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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (LOG
    -0.07
    RAW
    -0.06
     boh
    -0.06
     ett
    -0.06
     dissatisfaction
    -0.06
    ului
    -0.06
     Jou
    -0.06
    ..."↵↵
    -0.06
    LOBAL
    -0.06
    .Movie
    -0.06
    POSITIVE LOGITS
    土
    0.07
    　　　　　　
    0.07
    _finished
    0.06
    segment
    0.06
    атора
    0.06
     badges
    0.06
     başvur
    0.06
    COR
    0.06
    Terrain
    0.06
     staple
    0.06
    Act Density 0.025%

    No Known Activations