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

    Neuronpedia

    INDEX
    Explanations

    Health insurance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    722
    -0.07
    asdf
    -0.07
     confrontation
    -0.07
    造成
    -0.07
    晓
    -0.06
    わり
    -0.06
    CallBack
    -0.06
     wagon
    -0.06
     сфері
    -0.06
     pantry
    -0.06
    POSITIVE LOGITS
    .exc
    0.07
     Elig
    0.06
     tone
    0.06
    _layer
    0.06
     služ
    0.06
     layer
    0.06
    .Sqrt
    0.06
    ƒ
    0.06
    iterator
    0.06
     resets
    0.06
    Act Density 0.039%

    No Known Activations