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

    Neuronpedia

    INDEX
    Explanations

    clauses expressing opinions, feelings or judgements

    oai_token-act-pair · gemini-2.0-flash

    personal anecdotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.85
     متعلقه
    -0.85
    AddTagHelper
    -0.76
    帖最后由
    -0.76
     autorytatywna
    -0.74
    IntoConstraints
    -0.70
    TintMode
    -0.69
    fjspx
    -0.68
     typelib
    -0.67
    PropertyChanging
    -0.66
    POSITIVE LOGITS
    multicolumn
    0.56
    enegal
    0.45
     what
    0.44
     Rocco
    0.44
    isci
    0.43
     special
    0.43
     pública
    0.42
     Special
    0.42
     important
    0.42
     unlike
    0.41
    Act Density 1.976%

    No Known Activations