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

    Neuronpedia

    INDEX
    Explanations

    alpha-numeric codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vz
    -0.08
    jmu
    -0.07
     случай
    -0.07
     Witnesses
    -0.06
    [z
    -0.06
     pornos
    -0.06
     rap
    -0.06
     fing
    -0.06
     Şu
    -0.06
     preseason
    -0.06
    POSITIVE LOGITS
     metadata
    0.06
    .Java
    0.06
     svn
    0.06
    肌
    0.06
    ERCHANTABILITY
    0.06
    ักษณ
    0.06
    BERT
    0.06
    inda
    0.06
    артам
    0.06
    Leave
    0.06
    Act Density 0.026%

    No Known Activations