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

    Neuronpedia

    INDEX
    Explanations

    acts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     succeeds
    -0.07
     Numeric
    -0.07
    .emf
    -0.06
    incipal
    -0.06
    entionPolicy
    -0.06
    SerializedName
    -0.06
    “And
    -0.06
    _One
    -0.06
    :;"
    -0.06
    “But
    -0.06
    POSITIVE LOGITS
     alınan
    0.07
     requiring
    0.06
     sour
    0.06
     unrecognized
    0.06
    कर
    0.06
    -speed
    0.06
     bother
    0.06
     phon
    0.06
    (src
    0.06
    水平
    0.06
    Act Density 0.000%

    No Known Activations