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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ब
    -0.07
     dép
    -0.07
    erre
    -0.07
     bankers
    -0.06
     ii
    -0.06
     Minimum
    -0.06
    InterfaceOrientation
    -0.06
    ’é
    -0.06
     s
    -0.06
    -ब
    -0.06
    POSITIVE LOGITS
     when
    0.08
     When
    0.08
     while
    0.08
     Chile
    0.07
     Anth
    0.07
    NASA
    0.07
    when
    0.07
     densely
    0.06
    렬
    0.06
    When
    0.06
    Act Density 0.046%

    No Known Activations