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

    Neuronpedia

    INDEX
    Explanations

    some [entity/group/opinion]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.81
     and
    0.79
    /
    0.78
     to
    0.75
     a
    0.74
    chnung
    0.71
     the
    0.71
     by
    0.71
    corr
    0.67
     /
    0.66
    POSITIVE LOGITS
    те
    0.82
    者は
    0.78
     kanë
    0.78
    티
    0.77
    ième
    0.77
    t
    0.76
    ુ
    0.75
     integrantes
    0.72
    ých
    0.72
     människor
    0.71
    Act Density 0.501%

    No Known Activations