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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional or psychological states and their effects

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

    punctuation and concluding words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.98
     nahilalakip
    -0.96
     ब्रेकडाउन
    -0.95
     CreateTagHelper
    -0.91
    DockStyle
    -0.84
    Personendaten
    -0.82
    -0.82
    AndEndTag
    -0.82
     يتيمه
    -0.81
    AddTagHelper
    -0.79
    POSITIVE LOGITS
     etc
    0.60
    etc
    0.47
     or
    0.34
    .
    0.34
    等等
    0.32
    extrême
    0.32
    None
    0.32
    and
    0.32
     Etc
    0.31
     all
    0.31
    Act Density 0.036%

    No Known Activations