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

    Neuronpedia

    INDEX
    Explanations

    annoying pests and nuisances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    1.12
     the
    1.02
     It
    1.02
     I
    0.98
    the
    0.89
    </h2>
    0.85
    0
    0.80
    hes
    0.80
    ize
    0.79
    ación
    0.77
    POSITIVE LOGITS
    l
    1.14
    EN
    1.13
    ES
    1.09
    AF
    1.02
    ג
    1.01
    ア
    0.99
    IS
    0.97
    ↵↵
    0.93
    З
    0.91
    ENT
    0.91
    Act Density 0.051%

    No Known Activations