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

    Neuronpedia

    INDEX
    Explanations

    listing alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    た
    0.45
     άλλο
    0.45
     μόνο
    0.45
     які
    0.42
     ശ്രീ
    0.42
     съ
    0.42
     да
    0.42
     этому
    0.41
     fă
    0.41
    yatiti
    0.41
    POSITIVE LOGITS
    5
    0.59
    8
    0.59
    4
    0.54
    Improve
    0.50
     has
    0.48
    0.48
    9
    0.48
    Eight
    0.47
    rma
    0.47
    6
    0.47
    Act Density 0.081%

    No Known Activations