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

    Neuronpedia

    INDEX
    Explanations

    AI model names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iconductor
    0.66
    yscanner
    0.66
    cosystem
    0.65
    ();
    0.64
    ventud
    0.62
    barung
    0.62
     تیار
    0.61
    ínas
    0.61
    ;&
    0.61
    æng
    0.61
    POSITIVE LOGITS
     Another
    1.16
     Anyway
    1.15
     So
    1.05
     Although
    1.02
     Besides
    1.01
     Perhaps
    1.00
     Yes
    1.00
    Another
    0.99
     We
    0.97
     Yeah
    0.97
    Act Density 0.001%

    No Known Activations