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

    Neuronpedia

    INDEX
    Explanations

    sunk cost fallacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fís
    -0.07
    Men
    -0.07
    馬
    -0.07
    .inf
    -0.06
    ्भ
    -0.06
    카
    -0.06
    ً،
    -0.06
    Attrs
    -0.06
    +h
    -0.06
     Düny
    -0.06
    POSITIVE LOGITS
     impacting
    0.06
     unanimously
    0.06
     viable
    0.06
    apiro
    0.06
    asm
    0.06
     buildup
    0.06
     proves
    0.06
    管理员
    0.06
     insign
    0.06
    _DIRECTORY
    0.06
    Act Density 0.080%

    No Known Activations