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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andin
    -0.07
     Больш
    -0.07
     بايد
    -0.06
    Automatic
    -0.06
     kilomet
    -0.06
    Thought
    -0.06
     amps
    -0.06
    atrice
    -0.06
    Sid
    -0.06
    _int
    -0.06
    POSITIVE LOGITS
    ivariate
    0.07
     ALLOW
    0.06
     filter
    0.06
     rallying
    0.06
     mult
    0.06
    ERA
    0.06
    Prices
    0.06
    .PackageManager
    0.06
     aunt
    0.06
    issues
    0.06
    Act Density 0.208%

    No Known Activations