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
    ₁
    -0.07
    _emlrt
    -0.06
    bor
    -0.06
    _cr
    -0.06
     얼마
    -0.06
    ’ll
    -0.06
     prose
    -0.06
    	TokenNameIdentifier
    -0.06
    ίτ
    -0.06
    ’ve
    -0.06
    POSITIVE LOGITS
     When
    0.07
    Whenever
    0.07
     despite
    0.07
    When
    0.07
     when
    0.07
    จ
    0.06
     Despite
    0.06
     Whenever
    0.06
    if
    0.06
    дая
    0.06
    Act Density 0.027%

    No Known Activations