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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fotbal
    -0.07
    ♀
    -0.06
     instead
    -0.06
     ii
    -0.06
     inning
    -0.06
    handled
    -0.06
    .each
    -0.06
     laz
    -0.06
    izabeth
    -0.06
    rar
    -0.06
    POSITIVE LOGITS
    ціональ
    0.08
    IDDEN
    0.07
    وسی
    0.07
    ρωπα
    0.06
    abric
    0.06
    際
    0.06
     ValidationResult
    0.06
    Americ
    0.06
    گیر
    0.06
    бас
    0.06
    Act Density 0.000%

    No Known Activations