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

    Neuronpedia

    INDEX
    Explanations

    Complicated/statistical/complex problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ultimo
    -0.08
    的那个
    -0.08
    养老服务
    -0.07
     nursing
    -0.07
    iquement
    -0.07
    .Question
    -0.07
     Counseling
    -0.07
    istros
    -0.07
     removes
    -0.07
    锌
    -0.07
    POSITIVE LOGITS
    _ability
    0.08
    ☴
    0.07
    Adventure
    0.07
    忙
    0.07
    بدأ
    0.06
    дви
    0.06
    0.06
    دراج
    0.06
    _contr
    0.06
    .disc
    0.06
    Act Density 0.153%

    No Known Activations