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

    Neuronpedia

    INDEX
    Explanations

    economic and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чною
    0.44
    щения
    0.43
     wielu
    0.42
     moderne
    0.41
     fraude
    0.41
     infrastrukt
    0.40
    Artista
    0.40
    Angry
    0.39
     podemos
    0.39
     potete
    0.39
    POSITIVE LOGITS
    镊
    0.47
     acidified
    0.46
     isotonic
    0.46
     stepwise
    0.44
     आणि
    0.42
     lengthwise
    0.42
     conjugates
    0.41
     metabolites
    0.41
     servings
    0.41
     orbits
    0.40
    Act Density 0.015%

    No Known Activations