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

    Neuronpedia

    INDEX
    Explanations

    programming loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Butyl
    0.44
    Bue
    0.42
    減少
    0.42
    Blooming
    0.41
    frying
    0.41
    水の
    0.41
    URNIZOR
    0.40
     λειτουργ
    0.39
     중요하다
    0.39
     Фургала
    0.39
    POSITIVE LOGITS
    for
    0.59
    if
    0.48
     for
    0.47
        
    0.46
    while
    0.46
     While
    0.44
    id
    0.43
    ;
    0.42
     For
    0.41
     hasn
    0.41
    Act Density 0.121%

    No Known Activations