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

    Neuronpedia

    INDEX
    Explanations

    ju words and api

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дра
    0.45
     इवन
    0.40
    देशी
    0.39
     vuccati
    0.39
    metter
    0.39
     метро
    0.38
    ledo
    0.38
     регули
    0.38
    قیع
    0.38
    दशी
    0.38
    POSITIVE LOGITS
     Juicy
    0.43
     Optionally
    0.38
     Mig
    0.38
     Box
    0.37
     Asset
    0.37
     NICE
    0.35
     Ju
    0.35
    Ju
    0.35
     NGS
    0.35
    hor
    0.35
    Act Density 0.001%

    No Known Activations