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

    Neuronpedia

    INDEX
    Explanations

    code syntax and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     which
    0.82
     has
    0.80
     who
    0.75
     extraordinaire
    0.75
     is
    0.73
     Announced
    0.70
     Information
    0.70
     consisting
    0.70
     Nonprofit
    0.69
     Innovative
    0.68
    POSITIVE LOGITS
    에서의
    0.66
    uradaki
    0.64
    ]}"
    0.63
     우리의
    0.62
     لە
    0.59
    }),
    0.59
    }'
    0.59
    }"
    0.58
    ítja
    0.58
    😵
    0.57
    Act Density 0.091%

    No Known Activations