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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нему
    -0.08
     Orch
    -0.07
    .lex
    -0.07
    posure
    -0.07
    لمة
    -0.06
    دهم
    -0.06
     Entrance
    -0.06
    upaten
    -0.06
     Mp
    -0.06
    мента
    -0.06
    POSITIVE LOGITS
     وب
    0.06
     Sentinel
    0.06
    нії
    0.06
     каз
    0.06
     člán
    0.06
    @GeneratedValue
    0.06
    expected
    0.06
    [R
    0.06
    .Value
    0.06
     يج
    0.06
    Act Density 0.060%

    No Known Activations