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
    arrass
    -0.07
    ören
    -0.07
    igraph
    -0.07
     limits
    -0.06
     cubes
    -0.06
    켜
    -0.06
    -hash
    -0.06
    рус
    -0.06
     handleMessage
    -0.06
     nud
    -0.06
    POSITIVE LOGITS
    ([
    0.07
     torchvision
    0.06
     CALLBACK
    0.06
    ₂
    0.06
     žena
    0.06
    ام
    0.06
     міс
    0.06
    �
    0.06
    궁
    0.06
     função
    0.06
    Act Density 0.014%

    No Known Activations