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

    Neuronpedia

    INDEX
    Explanations

    .Serialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一个人
    -0.07
    sey
    -0.07
    ун
    -0.06
     людям
    -0.06
     situ
    -0.06
    _network
    -0.06
     راه
    -0.06
     cuck
    -0.06
    _rsp
    -0.06
    _utf
    -0.06
    POSITIVE LOGITS
    .Serialization
    0.09
    .PERMISSION
    0.07
     genital
    0.07
    heels
    0.06
     мо
    0.06
     instal
    0.06
     entrance
    0.06
    vil
    0.06
    .il
    0.06
     cartesian
    0.06
    Act Density 0.001%

    No Known Activations