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

    Neuronpedia

    INDEX
    Explanations

    self or independent actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protégé
    0.44
    Ну
    0.44
     বাঙালী
    0.42
    Pb
    0.41
    ንን
    0.41
     डाउनलोड
    0.41
     Downloading
    0.40
     Additional
    0.40
     rechte
    0.40
    SIBILITY
    0.39
    POSITIVE LOGITS
    自助
    0.42
     patio
    0.40
     Patio
    0.38
     bitters
    0.36
     Shrine
    0.36
     independent
    0.36
     workouts
    0.36
     cross
    0.36
    workouts
    0.36
     self
    0.35
    Act Density 0.000%

    No Known Activations