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

    Neuronpedia

    INDEX
    Explanations

    branding and identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implements
    0.53
     holog
    0.51
    oggler
    0.51
    '}
    0.51
     Holog
    0.50
     tires
    0.49
     Foli
    0.47
     browned
    0.47
     converted
    0.46
    )}}
    0.46
    POSITIVE LOGITS
    ルイ
    0.55
    瀋
    0.48
    られる
    0.48
    сто
    0.46
    ש
    0.46
    ੯
    0.45
    ष्टी
    0.45
    そのような
    0.45
    fifty
    0.45
    читы
    0.44
    Act Density 0.000%

    No Known Activations