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

    Neuronpedia

    INDEX
    Explanations

    stablecoins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blowing
    0.58
     grind
    0.57
     rejoindre
    0.52
     narrowing
    0.52
     patriarch
    0.51
     চালিয়ে
    0.50
     cinco
    0.49
     florist
    0.49
    К
    0.48
     vét
    0.48
    POSITIVE LOGITS
    다
    0.72
    an
    0.70
    ان
    0.65
    は
    0.63
    منٹ
    0.57
    onError
    0.54
    am
    0.54
    Layout
    0.54
    는
    0.53
    parameters
    0.52
    Act Density 0.001%

    No Known Activations