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

    Neuronpedia

    INDEX
    Explanations

    psychosocial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {{/
    -0.72
     незавершена
    -0.65
     bubble
    -0.63
    -0.63
    ThroughAttribute
    -0.61
     surla
    -0.60
    <?
    -0.60
     وتسجيلات
    -0.60
     autorytatywna
    -0.59
    AddTagHelper
    -0.59
    POSITIVE LOGITS
    nt
    0.57
    sp
    0.56
    r
    0.55
    bed
    0.55
    son
    0.55
    ron
    0.53
    ap
    0.50
    بوابة
    0.49
    tre
    0.49
    rys
    0.49
    Act Density 0.016%

    No Known Activations