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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     पड़े
    -0.07
     settled
    -0.07
     Subsequently
    -0.07
    imeters
    -0.07
     ঘটন
    -0.07
     abges
    -0.07
    <Assembly
    -0.07
    \",\
    -0.07
     boarded
    -0.07
    被
    -0.07
    POSITIVE LOGITS
     complicated
    0.08
     complicado
    0.08
    ాంక
    0.08
    CHO
    0.08
     indique
    0.08
     personnalis
    0.08
     customize
    0.08
     berupa
    0.07
     obligatorio
    0.07
     personalizado
    0.07
    Act Density 0.004%

    No Known Activations