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

    Neuronpedia

    INDEX
    Explanations

    latching mechanisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slov
    -0.07
     contemplating
    -0.07
     lay
    -0.07
     política
    -0.07
    Uploader
    -0.06
    ullets
    -0.06
     exhausted
    -0.06
    .router
    -0.06
     verm
    -0.06
    ib
    -0.06
    POSITIVE LOGITS
    กรณ
    0.07
    /from
    0.06
    rence
    0.06
    paint
    0.06
     SAFE
    0.06
     false
    0.06
     rampant
    0.06
     jTable
    0.06
    TexImage
    0.06
     kork
    0.06
    Act Density 0.007%

    No Known Activations