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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     justified
    -0.08
     Temper
    -0.07
     sonic
    -0.07
    -headed
    -0.07
     également
    -0.06
     Index
    -0.06
     feasibility
    -0.06
    _vars
    -0.06
    attles
    -0.06
     PATH
    -0.06
    POSITIVE LOGITS
     Merch
    0.07
    ậ
    0.07
    े↵
    0.06
     beş
    0.06
    î
    0.06
     faucet
    0.06
    .Help
    0.06
    length
    0.06
    ULONG
    0.06
    /logo
    0.06
    Act Density 0.020%

    No Known Activations