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

    Neuronpedia

    INDEX
    Explanations

    instructions or prerequisites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )$}
    0.53
     Lich
    0.53
     કોઈ
    0.49
    もの
    0.47
     Adobe
    0.46
     gotas
    0.45
    তায়
    0.45
    めの
    0.45
     Watson
    0.45
    恒
    0.45
    POSITIVE LOGITS
    iska
    0.50
    ducting
    0.47
    isk
    0.47
    uline
    0.47
    itten
    0.46
    undred
    0.46
    argout
    0.45
    oue
    0.45
    ål
    0.45
     yılında
    0.45
    Act Density 0.000%

    No Known Activations