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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qualitative
    -0.07
     nextState
    -0.06
     Sender
    -0.06
    ()=>
    -0.06
    薄
    -0.06
    。
    -0.06
    intl
    -0.06
    brew
    -0.06
    _nbr
    -0.06
    quets
    -0.06
    POSITIVE LOGITS
     Fraction
    0.06
     advances
    0.06
    _RW
    0.06
     ми
    0.06
    ificaciones
    0.06
     Very
    0.06
    polator
    0.06
    务
    0.06
     desperately
    0.06
     dust
    0.06
    Act Density 0.008%

    No Known Activations