Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluations or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding common verbs or actions

    np_acts-logits-general · gemini-2.0-flash

    collocations like "friendly match," "cache miss," "bidding war"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.50
     prête
    -0.47
    XDECREF
    -0.46
    vinner
    -0.46
    ativement
    -0.46
    ուն
    -0.42
    ุน
    -0.42
     fragile
    -0.42
    ylate
    -0.41
     adopting
    -0.41
    POSITIVE LOGITS
     CascadeType
    0.73
     Chwiliwch
    0.73
    adpleegd
    0.73
    Personensuche
    0.72
     session
    0.72
     мәкал
    0.68
    InputBorder
    0.68
    TemporalType
    0.67
     sessions
    0.66
     Himo
    0.66
    Act Density 0.864%

    No Known Activations