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

    Neuronpedia

    INDEX
    Explanations

    modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    which
    0.66
    '.
    0.65
    C
    0.65
    end
    0.64
    BQ
    0.64
    how
    0.61
    de
    0.61
    what
    0.61
    ow
    0.59
    of
    0.59
    POSITIVE LOGITS
     myös
    0.93
     it
    0.88
     Außerdem
    0.86
     arī
    0.82
     بھی
    0.81
     there
    0.80
     inoltre
    0.79
     उन्हें
    0.78
     keiner
    0.78
     भी
    0.77
    Act Density 0.002%

    No Known Activations