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

    Neuronpedia

    INDEX
    Explanations

    passwords and combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proporciona
    0.50
     consequências
    0.47
     accomplish
    0.46
    hma
    0.46
     Nós
    0.45
    nja
    0.45
     обсужда
    0.45
     sigui
    0.44
    hém
    0.44
     suivant
    0.43
    POSITIVE LOGITS
    )}}{
    0.53
    )}}{\
    0.46
    )}\
    0.44
    )}=
    0.41
     theorist
    0.41
     *}
    0.40
     shrou
    0.40
    '):
    0.40
     దు
    0.39
     zombies
    0.39
    Act Density 0.002%

    No Known Activations