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

    Neuronpedia

    INDEX
    Explanations

    concepts or specific works

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Because
    0.56
     harmless
    0.55
     Discuss
    0.54
     Establishment
    0.54
    推荐
    0.54
    tum
    0.53
    ụn
    0.53
    lul
    0.52
    fellow
    0.52
    कुम
    0.51
    POSITIVE LOGITS
     desejo
    0.65
     bội
    0.63
     voyages
    0.61
     uprising
    0.59
     propulsion
    0.59
     πλη
    0.58
     overdrive
    0.58
    pulsewidth
    0.57
     sciatic
    0.57
     ಉತ್ತ
    0.57
    Act Density 0.000%

    No Known Activations