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

    Neuronpedia

    INDEX
    Explanations

    mutation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immature
    -0.07
     действительно
    -0.07
    (bean
    -0.07
    .perform
    -0.07
    ñana
    -0.07
     الليبي
    -0.07
    焙
    -0.07
    _construct
    -0.07
    咋
    -0.07
     Straßen
    -0.07
    POSITIVE LOGITS
     MU
    0.06
    移送
    0.06
    lined
    0.06
    CLIENT
    0.06
    OAuth
    0.06
    war
    0.06
    Vel
    0.06
    疾病的
    0.06
    _INTERNAL
    0.06
    𝓸
    0.06
    Act Density 0.020%

    No Known Activations