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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shepherd
    -0.07
     wagon
    -0.06
     parl
    -0.06
    τις
    -0.06
    _movie
    -0.06
    خته
    -0.06
     ais
    -0.06
    ety
    -0.06
     alliances
    -0.06
     nặng
    -0.06
    POSITIVE LOGITS
    (SQL
    0.06
    Valid
    0.06
    أك
    0.06
    otte
    0.06
     srov
    0.06
     Conor
    0.06
    CONS
    0.06
     Pret
    0.06
    intr
    0.06
    ▍
    0.06
    Act Density 0.147%

    No Known Activations