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

    Neuronpedia

    INDEX
    Explanations

    Taxes and financial responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μπ
    -0.07
    addin
    -0.07
    Damage
    -0.07
     trio
    -0.07
    .trace
    -0.06
     Bangalore
    -0.06
     PERMISSION
    -0.06
     stress
    -0.06
    рен
    -0.06
    рина
    -0.06
    POSITIVE LOGITS
    activ
    0.07
     PAC
    0.06
    ейств
    0.06
    dim
    0.06
     setState
    0.06
     taxpayers
    0.06
    oser
    0.06
    otyp
    0.06
     Vect
    0.06
    Multip
    0.06
    Act Density 0.056%

    No Known Activations