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

    Neuronpedia

    INDEX
    Explanations

    Sunk cost and worker bias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonzero
    -0.07
    342
    -0.06
    516
    -0.06
    .Make
    -0.06
    ibrated
    -0.06
    ека
    -0.06
    634
    -0.06
    िद
    -0.06
    utility
    -0.06
     Stainless
    -0.06
    POSITIVE LOGITS
     disen
    0.06
    ل
    0.06
    kHz
    0.06
    辺
    0.06
     ring
    0.06
     Lomb
    0.06
    ٬
    0.06
     iy
    0.06
    .fileName
    0.06
     бар
    0.06
    Act Density 0.101%

    No Known Activations