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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilité
    -0.08
     Complaint
    -0.07
    JNI
    -0.06
     Sidebar
    -0.06
     Biden
    -0.06
    Cast
    -0.06
    array
    -0.06
     diagonal
    -0.06
    iness
    -0.06
    _det
    -0.06
    POSITIVE LOGITS
    .todos
    0.07
     dahil
    0.07
    喔
    0.06
    _REFRESH
    0.06
    /manage
    0.06
    islav
    0.06
     drawers
    0.06
    esper
    0.06
     её
    0.06
    �
    0.06
    Act Density 0.027%

    No Known Activations