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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     апреля
    -0.08
     mujer
    -0.08
     toc
    -0.07
     capped
    -0.07
    좍
    -0.07
     intimidated
    -0.07
     ноября
    -0.07
     presumption
    -0.06
    停下来
    -0.06
    cause
    -0.06
    POSITIVE LOGITS
    phans
    0.07
    IFO
    0.07
    知識
    0.07
     Running
    0.07
     evils
    0.07
    MODEL
    0.07
    GM
    0.07
     DATA
    0.07
     Hv
    0.07
     TAS
    0.06
    Act Density 0.006%

    No Known Activations