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

    Neuronpedia

    INDEX
    Explanations

    market share growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _.
    0.43
    ずつ
    0.40
     anisot
    0.39
     psychos
    0.39
     OPCODE
    0.39
     Physiol
    0.38
    醐
    0.38
     isotropic
    0.37
     قریب
    0.37
     verticals
    0.37
    POSITIVE LOGITS
    ahaman
    0.40
     copies
    0.40
    che
    0.39
     houden
    0.37
    विल
    0.37
     feeling
    0.37
     Copies
    0.37
     doubts
    0.36
    discount
    0.36
     Carlo
    0.36
    Act Density 0.002%

    No Known Activations