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

    Neuronpedia

    INDEX
    Explanations

    already

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loggedin
    -0.07
     pokoj
    -0.07
    ulis
    -0.07
    万円
    -0.07
    -append
    -0.06
    .ingredients
    -0.06
    Vin
    -0.06
     utens
    -0.06
    Spacer
    -0.06
    .putInt
    -0.06
    POSITIVE LOGITS
     already
    0.08
    DY
    0.07
     Execute
    0.07
    /$
    0.06
     이미
    0.06
     PRE
    0.06
    LOS
    0.06
    Simply
    0.06
     Already
    0.06
    Already
    0.06
    Act Density 0.010%

    No Known Activations