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

    Neuronpedia

    INDEX
    Explanations

    equations and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).)
    0.58
    <unused402>
    0.57
    )_
    0.57
    iscale
    0.57
    ）』
    0.57
    ))}
    0.56
    ус
    0.56
    etrain
    0.55
    ').
    0.55
    Kelly
    0.54
    POSITIVE LOGITS
     default
    0.64
     Posted
    0.62
    デフォルト
    0.61
     Están
    0.61
    ཥ
    0.61
    皑
    0.60
     negatively
    0.60
     Lúc
    0.60
     firebase
    0.60
    ඍ
    0.59
    Act Density 0.015%

    No Known Activations