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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Formula
    -0.06
    高
    -0.06
    Ral
    -0.06
    -Jul
    -0.06
     Jord
    -0.06
    Area
    -0.06
     nă
    -0.06
    Clientes
    -0.06
    áy
    -0.06
    元
    -0.06
    POSITIVE LOGITS
     DIM
    0.07
     бюджет
    0.06
     Happ
    0.06
     opposed
    0.06
     shaved
    0.06
     Thai
    0.06
     accept
    0.06
    -secondary
    0.06
     Pending
    0.06
    .debug
    0.06
    Act Density 0.016%

    No Known Activations