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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    existence
    -0.07
    _AB
    -0.07
    istencia
    -0.07
     derives
    -0.07
    Handles
    -0.07
    似的
    -0.07
     devil
    -0.06
    _CLR
    -0.06
     promin
    -0.06
     jedno
    -0.06
    POSITIVE LOGITS
    Airport
    0.06
     examine
    0.06
    brit
    0.06
    邮箱
    0.06
    Ip
    0.06
    _checker
    0.06
     procur
    0.06
    icemail
    0.06
    pper
    0.06
    Sweet
    0.06
    Act Density 0.000%

    No Known Activations