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

    Neuronpedia

    INDEX
    Explanations

    parties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zinc
    -0.07
    _inverse
    -0.07
     breathe
    -0.07
    quir
    -0.07
     horr
    -0.07
    תר
    -0.07
     ie
    -0.06
    inaire
    -0.06
    土耳其
    -0.06
     haci
    -0.06
    POSITIVE LOGITS
     culture
    0.08
    ].
    0.08
    Sh
    0.07
    爬上
    0.07
     Rolling
    0.07
     DateTimeOffset
    0.07
    .FileName
    0.06
    歳
    0.06
    Before
    0.06
    Enumer
    0.06
    Act Density 0.002%

    No Known Activations