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
    2
    -0.09
    4
    -0.08
    το
    -0.07
     IonicModule
    -0.07
    ir
    -0.07
    �
    -0.07
    ar
    -0.07
    i
    -0.07
    clide
    -0.07
    a
    -0.06
    POSITIVE LOGITS
     when
    0.21
    when
    0.18
     When
    0.17
    When
    0.16
     WHEN
    0.16
    "When
    0.13
    .when
    0.13
    “When
    0.12
    .When
    0.12
    	when
    0.12
    Act Density 0.113%

    No Known Activations