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

    Neuronpedia

    INDEX
    Explanations

    have to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    деся
    0.63
    kD
    0.61
    cü
    0.60
    哎
    0.59
    部
    0.59
     discoloration
    0.59
    pw
    0.58
    }&=
    0.57
    бло
    0.57
     brane
    0.57
    POSITIVE LOGITS
    $\
    0.75
     dragged
    0.67
    ள்
    0.66
    लोड
    0.65
    ty
    0.65
    quadratic
    0.62
    $("
    0.61
    $,
    0.61
    $('
    0.61
    $.
    0.61
    Act Density 0.017%

    No Known Activations