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

    Neuronpedia

    INDEX
    Explanations

    .Column or .Row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    psilon
    -0.08
    áp
    -0.07
     DropIndex
    -0.07
     Tehran
    -0.07
     Henderson
    -0.07
    _GE
    -0.07
     interess
    -0.07
    .today
    -0.07
     Vulcan
    -0.07
    这对于
    -0.07
    POSITIVE LOGITS
     Number
    0.07
    씩
    0.07
    一定的
    0.07
    _UNLOCK
    0.06
     LOT
    0.06
    ግ
    0.06
     vraiment
    0.06
     OS
    0.06
    _ht
    0.06
    账号
    0.06
    Act Density 0.001%

    No Known Activations