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

    Neuronpedia

    INDEX
    Explanations

    vk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imb
    -0.07
     blo
    -0.07
    襲
    -0.06
    齐全
    -0.06
     TP
    -0.06
    onor
    -0.06
    ondheim
    -0.06
     cumbersome
    -0.06
    亡
    -0.06
     TYPE
    -0.06
    POSITIVE LOGITS
    呖
    0.08
     minerals
    0.08
     permite
    0.07
    <translation
    0.07
     Disk
    0.07
     relations
    0.07
    edelta
    0.07
    _relations
    0.07
     sluts
    0.07
    𝛿
    0.07
    Act Density 0.001%

    No Known Activations