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

    Neuronpedia

    INDEX
    Explanations

    mium and Nd

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itoris
    -0.07
     nunca
    -0.07
     InkWell
    -0.07
     Mansion
    -0.07
    呐
    -0.07
     cinematic
    -0.07
    经验
    -0.07
     Jon
    -0.06
     consciously
    -0.06
     FIR
    -0.06
    POSITIVE LOGITS
    (sw
    0.07
    .rpm
    0.07
    _UNSUPPORTED
    0.07
    主管部门
    0.07
    %,
    0.07
     problemas
    0.07
    繁忙
    0.06
    相关部门
    0.06
    配备
    0.06
    росл
    0.06
    Act Density 0.008%

    No Known Activations