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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odes
    -0.07
     như
    -0.06
    ющего
    -0.06
    vehicles
    -0.06
    ानत
    -0.06
     либо
    -0.06
     Dil
    -0.06
     carriage
    -0.06
    poz
    -0.06
    لود
    -0.06
    POSITIVE LOGITS
     toJson
    0.08
     Zimbabwe
    0.07
     Nicholas
    0.07
     SUP
    0.07
    iflower
    0.06
     　 　 　
    0.06
    "},
    0.06
     ellipse
    0.06
    evento
    0.06
     filtro
    0.06
    Act Density 0.060%

    No Known Activations