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

    Neuronpedia

    INDEX
    Explanations

    bring back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.79
    ↵
    0.75
    okhlov
    0.65
    lı
    0.61
     eggplant
    0.59
    lld
    0.58
    cite
    0.57
    ure
    0.57
    cute
    0.57
    什么是
    0.56
    POSITIVE LOGITS
    ität
    0.95
    años
    0.72
     thường
    0.68
     ধরনের
    0.67
    itä
    0.67
     REACTORS
    0.66
    ጷ
    0.66
    ductory
    0.66
    éfonos
    0.66
    ਵਾ
    0.65
    Act Density 0.283%

    No Known Activations