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

    Neuronpedia

    INDEX
    Explanations

    actions or plans for roles and degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.60
    ри
    0.56
    '
    0.48
     heating
    0.47
     [
    0.46
     гото
    0.46
    <0x80>
    0.45
    続け
    0.45
    <0xAA>
    0.44
    نگ
    0.44
    POSITIVE LOGITS
    w
    0.70
    on
    0.66
    sby
    0.63
     Gambia
    0.61
    یت
    0.61
     Cach
    0.61
    "})
    0.61
     Chac
    0.60
    ב
    0.60
     Беларусь
    0.59
    Act Density 0.000%

    No Known Activations