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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Converter
    -0.08
    乌
    -0.08
    _LARGE
    -0.07
     fades
    -0.07
    Envelope
    -0.07
    玛丽
    -0.07
    Earlier
    -0.07
     narz
    -0.07
    createFrom
    -0.07
    🐰
    -0.07
    POSITIVE LOGITS
     abilities
    0.08
    b
    0.07
    成为
    0.07
    monic
    0.06
    oins
    0.06
     employ
    0.06
    sn
    0.06
     Adjust
    0.06
    icrobial
    0.06
    اعد
    0.06
    Act Density 0.026%

    No Known Activations