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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    畏
    0.47
     гульнявыя
    0.43
    告知
    0.43
    жек
    0.42
    γρά
    0.42
    会让
    0.42
    让
    0.42
    ចុ
    0.41
    Spider
    0.41
     Armando
    0.41
    POSITIVE LOGITS
    isecond
    0.57
    PDE
    0.47
    OD
    0.46
     հատ
    0.44
     grosso
    0.43
     weddings
    0.43
     populations
    0.42
     resettlement
    0.41
     satellites
    0.41
     derived
    0.41
    Act Density 0.000%

    No Known Activations