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

    Neuronpedia

    INDEX
    Explanations

    Crisis text line, crucially important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ური
    3.28
    eo
    2.68
    ята
    2.63
     kinks
    2.60
     traff
    2.59
    ̪
    2.49
    𝓬
    2.49
     trac
    2.48
    接種
    2.47
     extremities
    2.45
    POSITIVE LOGITS
    פ
    2.76
    пто
    2.73
    ণের
    2.69
    ত্রিম
    2.65
     tama
    2.65
     tende
    2.58
     HttpResponse
    2.56
     pensando
    2.51
    蟀
    2.46
    ťou
    2.42
    Act Density 0.529%

    No Known Activations