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

    Neuronpedia

    INDEX
    Explanations

    itself followed by punctuation or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    part
    0.93
    correspond
    0.93
    clip
    0.92
     vostro
    0.91
    probability
    0.91
    ichter
    0.90
    lihat
    0.90
    ➡️
    0.87
    healthcare
    0.87
    confirmation
    0.87
    POSITIVE LOGITS
     \{
    0.96
    に
    0.94
     $\{\
    0.90
     uttered
    0.89
    招标文件
    0.88
     е
    0.87
    м
    0.86
    ം
    0.84
     fique
    0.83
    ни
    0.83
    Act Density 0.071%

    No Known Activations