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

    Neuronpedia

    INDEX
    Explanations

    Let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phía
    -0.08
    WORK
    -0.07
    _empty
    -0.07
    惴
    -0.07
    芫
    -0.07
    _lower
    -0.07
    שואה
    -0.07
    lığını
    -0.07
    lope
    -0.07
    ้อย
    -0.07
    POSITIVE LOGITS
     качеств
    0.07
    Christmas
    0.06
     Geme
    0.06
     objectives
    0.06
     Aw
    0.06
     Crus
    0.06
    .Bl
    0.06
    Needs
    0.06
    _own
    0.06
    ,Th
    0.06
    Act Density 0.006%

    No Known Activations