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

    Neuronpedia

    INDEX
    Explanations

    Describes qualities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gboolean
    -0.07
    Для
    -0.07
    .union
    -0.07
    apur
    -0.07
    benh
    -0.07
    ccak
    -0.06
     اهم
    -0.06
     Cohen
    -0.06
     NAMES
    -0.06
    .DIS
    -0.06
    POSITIVE LOGITS
    付
    0.07
     Powered
    0.07
    /entities
    0.06
     Infos
    0.06
     LM
    0.06
     sebuah
    0.06
    �
    0.06
    阅
    0.06
     Approved
    0.06
     endings
    0.06
    Act Density 0.089%

    No Known Activations