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

    Neuronpedia

    INDEX
    Explanations

    reconsider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    消失
    -0.07
     eminent
    -0.07
     hiç
    -0.07
    ☰
    -0.07
    Services
    -0.07
     deadlock
    -0.07
    itus
    -0.07
    騰
    -0.07
    ValueCollection
    -0.07
    bai
    -0.06
    POSITIVE LOGITS
    udiante
    0.07
    小姐
    0.07
    _obj
    0.06
    好坏
    0.06
     $
    0.06
    +");↵
    0.06
    жу
    0.06
    .grade
    0.06
    .cz
    0.06
    //------------------------------------------------------------------------------↵
    0.06
    Act Density 0.018%

    No Known Activations