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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weapon
    -0.07
     fün
    -0.06
     mir
    -0.06
    _mock
    -0.06
     bons
    -0.06
     confession
    -0.06
     gros
    -0.06
    �
    -0.06
    ضو
    -0.06
    áře
    -0.06
    POSITIVE LOGITS
     Sight
    0.07
    .credit
    0.07
     stdClass
    0.07
     Cougar
    0.07
    .STATUS
    0.07
    .FlatStyle
    0.07
    dG
    0.06
    0.06
     perplex
    0.06
     Д
    0.06
    Act Density 0.022%

    No Known Activations