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

    Neuronpedia

    INDEX
    Explanations

    itive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prescriptions
    -0.09
     incó
    -0.08
     inscrição
    -0.08
     провод
    -0.08
     Quiz
    -0.08
     substrates
    -0.07
     Enfer
    -0.07
     prescription
    -0.07
     enfer
    -0.07
     butterfly
    -0.07
    POSITIVE LOGITS
     greed
    0.08
    eps
    0.08
     Lips
    0.08
     fulfilled
    0.08
     spite
    0.08
    -hearted
    0.08
    So
    0.07
    arski
    0.07
     appetite
    0.07
     greedy
    0.07
    Act Density 0.005%

    No Known Activations