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

    Neuronpedia

    INDEX
    Explanations

    sequences containing the digit 6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hypothesis
    1.12
    hypothesis
    1.09
     hypothesis
    1.04
    Hyp
    1.01
     hypotheses
    0.98
     nulle
    0.95
     hipótesis
    0.95
     Hyp
    0.92
     máu
    0.87
    itivos
    0.85
    POSITIVE LOGITS
    bower
    0.76
     produ
    0.74
    anim
    0.73
    ou
    0.73
    motionProxy
    0.73
    err
    0.71
    addy
    0.70
    round
    0.69
     stear
    0.69
    ation
    0.69
    Act Density 0.045%

    No Known Activations