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

    Neuronpedia

    INDEX
    Explanations

    urging deeper consideration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UNKNOWN
    -0.07
     Transport
    -0.07
    leştirme
    -0.07
    ティ
    -0.07
    的历史
    -0.06
    なくても
    -0.06
    deaux
    -0.06
    aciones
    -0.06
     Delegate
    -0.06
    sWith
    -0.06
    POSITIVE LOGITS
    (Conv
    0.08
     carve
    0.07
     glBind
    0.07
    EncodingException
    0.07
    ➵
    0.07
    ,res
    0.07
    캠
    0.07
    -reset
    0.07
    .Dial
    0.07
     magician
    0.07
    Act Density 0.096%

    No Known Activations