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

    Neuronpedia

    INDEX
    Explanations

    privacy policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     జి
    0.46
    Electronics
    0.41
     пові
    0.41
    Bij
    0.40
     Bij
    0.38
    ボン
    0.38
     coltiv
    0.38
     wetensch
    0.38
    麵
    0.38
     Facult
    0.37
    POSITIVE LOGITS
     cast
    0.42
    cast
    0.40
    reader
    0.38
     descent
    0.37
    uchsia
    0.36
     located
    0.36
     inherent
    0.36
    lh
    0.36
    town
    0.36
    orse
    0.36
    Act Density 0.000%

    No Known Activations