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

    Neuronpedia

    INDEX
    Explanations

    _r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slipping
    -0.07
     özgür
    -0.07
     comfy
    -0.07
    rtype
    -0.07
    Cross
    -0.07
     XP
    -0.06
     North
    -0.06
     PLUGIN
    -0.06
    .publish
    -0.06
    .parts
    -0.06
    POSITIVE LOGITS
    ней
    0.06
    رسی
    0.06
    454
    0.06
    سي
    0.06
     years
    0.06
     matrices
    0.06
    运行
    0.06
     транспорт
    0.06
     �
    0.06
    trap
    0.06
    Act Density 0.000%

    No Known Activations