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

    Neuronpedia

    INDEX
    Explanations

    .R

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clientele
    -0.07
     sedan
    -0.07
    Pictures
    -0.07
    Extend
    -0.07
    jb
    -0.07
     TreeMap
    -0.06
    屋子
    -0.06
    也就
    -0.06
     Thumbnails
    -0.06
    โซ
    -0.06
    POSITIVE LOGITS
    рас
    0.08
    �
    0.07
     interpolation
    0.07
    问询
    0.07
     ransom
    0.07
    .Inter
    0.07
    不忘初心
    0.07
    rf
    0.07
    wart
    0.07
    inn
    0.07
    Act Density 0.000%

    No Known Activations