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

    Neuronpedia

    INDEX
    Explanations

    words following 'following' or 'next'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beatCounter
    0.49
     כ
    0.48
     ಔ
    0.45
     בי
    0.45
    నాలను
    0.45
     מה
    0.44
    शंस
    0.44
    ificance
    0.44
     সরিয়ে
    0.44
     맞
    0.43
    POSITIVE LOGITS
    doi
    0.44
    ENER
    0.44
    Tower
    0.43
    i
    0.43
     Teaching
    0.43
     Tower
    0.42
    Aph
    0.42
     Towers
    0.42
    ein
    0.41
    Gal
    0.41
    Act Density 0.000%

    No Known Activations