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

    Neuronpedia

    INDEX
    Explanations

    common name and phrase completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sulph
    0.44
     Tren
    0.44
     INS
    0.43
     Ins
    0.43
     Mineral
    0.43
     Simult
    0.42
    ن
    0.42
     intégral
    0.41
     T
    0.41
     Ric
    0.41
    POSITIVE LOGITS
     सूची
    0.56
    Breast
    0.51
    ask
    0.50
    war
    0.50
    emen
    0.49
    poon
    0.49
    the
    0.48
    hl
    0.48
    pper
    0.48
    ecake
    0.48
    Act Density 0.000%

    No Known Activations