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

    Neuronpedia

    INDEX
    Explanations

    part 1 or phase 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     variability
    0.40
     Variability
    0.40
    ystick
    0.39
    rying
    0.38
    腕
    0.38
    রেক
    0.37
     Lamp
    0.37
    umsi
    0.37
    ゥム
    0.37
     AnyObject
    0.37
    POSITIVE LOGITS
    Phase
    0.58
     Fase
    0.57
     halves
    0.57
     fases
    0.57
     phases
    0.53
     phase
    0.51
     Phases
    0.51
     phased
    0.51
    phase
    0.50
     fase
    0.50
    Act Density 0.052%

    No Known Activations