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

    Neuronpedia

    INDEX
    Explanations

    amilies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '],$
    -0.07
     caps
    -0.07
     hybrid
    -0.07
     Terrorism
    -0.06
     blanc
    -0.06
     Went
    -0.06
    ();↵↵↵
    -0.06
    --
    -0.06
     butter
    -0.06
     ruined
    -0.06
    POSITIVE LOGITS
    kish
    0.07
    �
    0.06
    ประกอบ
    0.06
    _fast
    0.06
    .chars
    0.06
    食べ
    0.06
    ام
    0.06
    .qt
    0.06
    _predictions
    0.06
    UNIX
    0.06
    Act Density 0.000%

    No Known Activations