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

    Neuronpedia

    INDEX
    Explanations

    insol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evaluations
    -0.07
     Carlo
    -0.07
     alleviate
    -0.06
     decisions
    -0.06
     mars
    -0.06
    ren
    -0.06
     two
    -0.06
     Victorian
    -0.06
    _positions
    -0.06
    202
    -0.06
    POSITIVE LOGITS
     kapı
    0.07
    /GL
    0.07
    .assertFalse
    0.07
    qrst
    0.07
    _pcm
    0.07
    ABS
    0.06
     Kaz
    0.06
    �
    0.06
     나가
    0.06
     embod
    0.06
    Act Density 0.001%

    No Known Activations