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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and evaluation metrics

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

    similarity or agreement

    np_acts-logits-general · gemini-2.0-flash

    similarity and correspondence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.58
    DotNetBar
    -0.54
     Phal
    -0.54
    -0.53
    .*")]
    -0.53
     resourceCulture
    -0.51
    Искәрмәләр
    -0.48
    ()?;
    -0.48
     Numerade
    -0.47
     Indem
    -0.46
    POSITIVE LOGITS
     ditto
    0.73
     elsewhere
    0.71
     similarly
    0.69
    同じく
    0.63
    MessageOf
    0.60
    Ditto
    0.59
    ditto
    0.58
     likewise
    0.57
    IntoConstraints
    0.55
     аналоги
    0.55
    Act Density 0.932%

    No Known Activations