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

    Neuronpedia

    INDEX
    Explanations

    gestures, nurses, power, village

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dylan
    0.44
    dach
    0.40
    意志
    0.40
    peers
    0.39
    Sad
    0.39
    Doll
    0.39
    intelligence
    0.39
    Modules
    0.38
    Tet
    0.38
    пти
    0.37
    POSITIVE LOGITS
     insignia
    0.41
     championships
    0.41
     '),
    0.41
     massive
    0.40
    thorpe
    0.40
     fpr
    0.40
     gemstone
    0.40
     championship
    0.39
    ruptcy
    0.39
     imput
    0.39
    Act Density 0.000%

    No Known Activations