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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ствует
    -0.07
    dataset
    -0.07
     range
    -0.07
     ccp
    -0.06
    _ob
    -0.06
     StreamWriter
    -0.06
     follows
    -0.06
    masına
    -0.06
     corporation
    -0.06
     Vương
    -0.06
    POSITIVE LOGITS
     narciss
    0.07
     �
    0.06
     خارجية
    0.06
    CHECK
    0.06
    Methods
    0.06
     sir
    0.06
    存档备份
    0.06
    ريع
    0.06
    entifier
    0.06
     psychotic
    0.05
    Act Density 0.016%

    No Known Activations