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

    Neuronpedia

    INDEX
    Explanations

    endpoint for specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.53
    in
    0.46
    ീയ
    0.45
    human
    0.44
    '.
    0.44
    pro
    0.43
    corporate
    0.43
    comment
    0.42
    traffic
    0.42
    fen
    0.42
    POSITIVE LOGITS
     어려운
    0.53
     этом
    0.52
    panelMenuList
    0.49
    т
    0.48
    Abu
    0.47
     структура
    0.46
     amyl
    0.46
    に行って
    0.46
     compares
    0.46
     алгорит
    0.45
    Act Density 0.003%

    No Known Activations