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

    Neuronpedia

    INDEX
    Explanations

    Forbes articles and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۶
    0.66
    HF
    0.66
    بی
    0.62
    άν
    0.61
    schools
    0.58
    یل
    0.57
    troops
    0.55
    Mkv
    0.54
    <0xB9>
    0.53
    MK
    0.52
    POSITIVE LOGITS
    '
    0.74
    "
    0.61
    it
    0.60
     види
    0.56
     cercanos
    0.55
     excre
    0.54
    ramiento
    0.54
     degener
    0.53
    "...
    0.51
     stave
    0.51
    Act Density 0.001%

    No Known Activations