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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gmail
    -0.07
     Beat
    -0.07
     Cat
    -0.07
     Proto
    -0.07
     Mys
    -0.07
     nasa
    -0.07
     PATH
    -0.07
     Arduino
    -0.07
    atian
    -0.07
     authoritarian
    -0.07
    POSITIVE LOGITS
     jeweils
    0.14
     ஆகிய
    0.12
     respectively
    0.11
     respectivamente
    0.10
     എന്നീ
    0.10
     എന്നിവ
    0.10
    都有
    0.09
     각각
    0.09
     соответственно
    0.09
     모두
    0.09
    Act Density 0.091%

    No Known Activations