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

    Neuronpedia

    INDEX
    Explanations

    clinical model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    æng
    0.57
    ising
    0.57
    ienze
    0.56
    otho
    0.55
    什么的
    0.54
    ৱ
    0.53
     prenez
    0.52
     sahaja
    0.51
    ياته
    0.50
     espécies
    0.50
    POSITIVE LOGITS
     clinically
    0.73
    阉
    0.71
     antisemit
    0.67
    MODEL
    0.66
    clinical
    0.65
     gynec
    0.64
     клини
    0.63
     تنظيم
    0.62
    clin
    0.59
     पार्टी
    0.59
    Act Density 0.001%

    No Known Activations