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

    Neuronpedia

    INDEX
    Explanations

    English and Spanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     humiliated
    0.69
     coaxial
    0.66
     ke
    0.66
     trưng
    0.62
     parallel
    0.61
     mail
    0.61
    escent
    0.60
     કરે
    0.57
    parallel
    0.56
     com
    0.56
    POSITIVE LOGITS
    レンチ
    0.89
    どり
    0.80
    பை
    0.77
    세를
    0.76
    érios
    0.74
     앱
    0.74
    elve
    0.73
     금
    0.72
    štění
    0.72
     ലഭ
    0.72
    Act Density 0.026%

    No Known Activations