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

    Neuronpedia

    INDEX
    Explanations

    in case or cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flexibles
    -1.14
    และ
    -1.08
     bronz
    -1.07
     flamen
    -1.06
    鰨
    -1.05
    '';
    -1.04
    ઁ
    -1.03
     applau
    -1.02
    त्तर
    -1.02
    depuis
    -1.00
    POSITIVE LOGITS
     if
    1.91
     cases
    1.73
    Some
    1.72
     case
    1.53
    When
    1.52
     Some
    1.47
     When
    1.44
    if
    1.41
    If
    1.40
     If
    1.38
    Act Density 0.043%

    No Known Activations