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

    Neuronpedia

    INDEX
    Explanations

    resistance bands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kemampuan
    0.67
    ellant
    0.60
     خلال
    0.59
    aran
    0.57
    adena
    0.57
     giardino
    0.57
     refreshment
    0.57
    amini
    0.57
     strumento
    0.55
     concierge
    0.55
    POSITIVE LOGITS
    को
    0.78
    자
    0.66
     matrices
    0.65
    އ
    0.64
    汚
    0.64
    ப
    0.63
     batches
    0.63
     et
    0.62
     buses
    0.61
    ن
    0.61
    Act Density 0.001%

    No Known Activations