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

    Neuronpedia

    INDEX
    Explanations

    special characters and newlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    器的
    0.92
     concentrated
    0.72
    器
    0.71
     PH
    0.65
     Te
    0.64
     coordinate
    0.64
     ll
    0.63
    кое
    0.61
     ร
    0.61
    ர
    0.60
    POSITIVE LOGITS
    nYou
    0.82
    f
    0.80
    ffield
    0.78
    nThe
    0.74
    fdata
    0.74
    u
    0.71
    <unused1797>
    0.70
    zA
    0.69
    d
    0.69
    identité
    0.69
    Act Density 0.140%

    No Known Activations