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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pled
    -0.07
     Surveillance
    -0.07
    㳚
    -0.07
    луш
    -0.07
    during
    -0.07
     Decision
    -0.07
     slipped
    -0.07
    enter
    -0.07
    宣告
    -0.07
    茫茫
    -0.07
    POSITIVE LOGITS
    agem
    0.07
    .fecha
    0.07
    arriv
    0.07
    агент
    0.07
    $args
    0.07
    Animations
    0.07
     rés
    0.07
    _platform
    0.06
    ódigo
    0.06
     princípio
    0.06
    Act Density 0.003%

    No Known Activations