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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divided
    -0.07
     HashMap
    -0.07
    _CANNOT
    -0.06
     institutions
    -0.06
    う
    -0.06
    oria
    -0.06
    umbo
    -0.06
    ::::::::::::
    -0.06
     cudd
    -0.06
    ORIA
    -0.06
    POSITIVE LOGITS
    .isTrue
    0.07
     للس
    0.07
     پیشنه
    0.06
     "");↵↵
    0.06
    .setTag
    0.06
    �
    0.06
     biod
    0.06
     منذ
    0.06
     s
    0.06
     D
    0.06
    Act Density 0.035%

    No Known Activations