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
    ρχ
    -0.07
     Campo
    -0.07
     hurt
    -0.07
     npm
    -0.06
     proxy
    -0.06
     Rene
    -0.06
    enders
    -0.06
     reject
    -0.06
    First
    -0.06
     元
    -0.06
    POSITIVE LOGITS
     Vac
    0.06
    operands
    0.06
    ickerView
    0.06
     crack
    0.06
    hydr
    0.06
    loom
    0.06
    (filtered
    0.06
    imers
    0.06
    communic
    0.06
    Office
    0.06
    Act Density 0.043%

    No Known Activations