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

    Neuronpedia

    INDEX
    Explanations

    travel certificates and protections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تراجع
    -0.08
     duż
    -0.07
    uddy
    -0.07
    opez
    -0.07
    _sup
    -0.07
    売れ
    -0.07
    rapper
    -0.07
    Tap
    -0.07
    唾
    -0.07
    Tw
    -0.07
    POSITIVE LOGITS
    锪
    0.07
    imens
    0.07
    .abstract
    0.07
     Finish
    0.07
     remover
    0.07
    征服
    0.07
    COMMON
    0.06
    >_
    0.06
    _Mode
    0.06
    酲
    0.06
    Act Density 0.000%

    No Known Activations