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

    Neuronpedia

    INDEX
    Explanations

    behold or hold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     भा
    0.40
     gen
    0.39
    升
    0.39
     clinical
    0.38
     nourr
    0.38
     abre
    0.37
     recid
    0.37
     regul
    0.37
     dental
    0.37
     outdoor
    0.36
    POSITIVE LOGITS
    }}.
    0.46
     রো
    0.38
     इनकार
    0.38
    ']].
    0.38
    >),
    0.38
    ēi
    0.37
    蔭
    0.37
    逊
    0.37
    လိ
    0.36
    šć
    0.36
    Act Density 0.002%

    No Known Activations