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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sample
    -0.07
     Identify
    -0.07
    nid
    -0.07
    ザ
    -0.07
    fixtures
    -0.07
     الذين
    -0.07
    .ball
    -0.07
    _servers
    -0.07
    团
    -0.06
    ندية
    -0.06
    POSITIVE LOGITS
     sesame
    0.06
    μένη
    0.06
     aus
    0.06
    ErrorException
    0.06
    Paragraph
    0.06
     tackle
    0.06
    Cases
    0.06
     Cases
    0.06
     babes
    0.06
     derin
    0.05
    Act Density 0.000%

    No Known Activations