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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ols
    -0.07
     Light
    -0.07
    -script
    -0.06
     stol
    -0.06
     Proxy
    -0.06
     repository
    -0.06
     alpha
    -0.06
     Hat
    -0.06
     ефектив
    -0.06
     heav
    -0.06
    POSITIVE LOGITS
    _DEV
    0.07
    革
    0.07
    fuscated
    0.07
    Compilation
    0.06
    REGISTER
    0.06
    시키
    0.06
     بنابر
    0.06
    =N
    0.06
    らく
    0.06
     Feed
    0.06
    Act Density 0.011%

    No Known Activations