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

    Neuronpedia

    INDEX
    Explanations

    credit card interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ЭС
    -0.08
     lua
    -0.08
    .sal
    -0.08
     cidades
    -0.08
     kub
    -0.07
    ipu
    -0.07
    cris
    -0.07
     गाव
    -0.07
     Nato
    -0.07
     vivimos
    -0.07
    POSITIVE LOGITS
     Bankruptcy
    0.10
     vicious
    0.09
     bankrupt
    0.09
     curvature
    0.09
     ratings
    0.08
     harsh
    0.08
     bankruptcy
    0.08
     penalties
    0.08
     тариф
    0.08
     afectados
    0.08
    Act Density 0.006%

    No Known Activations