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

    Neuronpedia

    INDEX
    Explanations

    data analysis/coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Content
    -0.08
    veget
    -0.07
    lenir
    -0.07
    번호
    -0.07
     demolition
    -0.06
     Room
    -0.06
    ifter
    -0.06
    ender
    -0.06
    />
    -0.06
     insulation
    -0.06
    POSITIVE LOGITS
    .Safe
    0.07
    _Runtime
    0.06
    .NAME
    0.06
    كومة
    0.06
     detain
    0.06
     dpi
    0.06
     TORT
    0.06
    ्शन
    0.06
    quoted
    0.06
    _od
    0.06
    Act Density 0.084%

    No Known Activations