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

    Neuronpedia

    INDEX
    Explanations

    mentions of scientific or research methodologies related to transitions between states

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

    Followed by Dutch words

    np_acts-logits-general · gemini-2.0-flash

    Dutch words starting with De

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agamemnon
    -0.54
    uppa
    -0.50
    Advertisement
    -0.50
     closer
    -0.47
    oen
    -0.46
     therefore
    -0.46
    }{*}{
    -0.46
    piel
    -0.45
     anyway
    -0.45
    zonego
    -0.45
    POSITIVE LOGITS
    šanai
    0.67
     obicei
    0.63
     vidare
    0.61
     varandra
    0.59
     huvud
    0.58
    InitVars
    0.58
    ValueStyle
    0.58
     laikā
    0.57
    følgelig
    0.57
     allmän
    0.57
    Act Density 0.012%

    No Known Activations