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

    Neuronpedia

    INDEX
    Explanations

    Articles "a" and "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     locations
    -0.06
     ві
    -0.06
     sorrow
    -0.06
    ики
    -0.06
    queries
    -0.06
     lectures
    -0.06
    _pwd
    -0.06
    ोध
    -0.06
    (vo
    -0.06
     fractions
    -0.06
    POSITIVE LOGITS
    jet
    0.06
    にして
    0.06
     mapper
    0.06
     countert
    0.06
    JT
    0.06
    ziej
    0.06
     Assass
    0.06
    .SuppressLint
    0.06
    :Object
    0.06
    Ans
    0.06
    Act Density 0.165%

    No Known Activations