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

    Neuronpedia

    INDEX
    Explanations

    torture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plage
    -0.07
     bloom
    -0.06
    GBP
    -0.06
     grandson
    -0.06
     DEALINGS
    -0.06
    lers
    -0.06
    rello
    -0.06
    یشن
    -0.06
     알
    -0.06
     staunch
    -0.06
    POSITIVE LOGITS
     torture
    0.10
     tortured
    0.09
    0.07
     Tort
    0.07
    0.07
    layouts
    0.06
    注意
    0.06
     Shot
    0.06
     во
    0.06
    extr
    0.06
    Act Density 0.002%

    No Known Activations