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

    Neuronpedia

    INDEX
    Explanations

    goes directly against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     พอ
    0.63
    lüssel
    0.62
     impotence
    0.62
    Женско
    0.61
    IONAL
    0.60
     ಪಾ
    0.60
     trace
    0.60
     bunt
    0.59
    ])-
    0.59
     gelato
    0.59
    POSITIVE LOGITS
    ре
    0.56
    汞
    0.54
     यूनिवर्स
    0.52
     against
    0.51
    वेग
    0.50
    лк
    0.50
    ach
    0.49
    against
    0.48
    ै
    0.48
    Slf
    0.48
    Act Density 0.050%

    No Known Activations