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

    Neuronpedia

    INDEX
    Explanations

    Celsius, temperature

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point number tokens (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .addObject
    -0.07
    .defaultValue
    -0.07
    .TabPage
    -0.07
     majestic
    -0.07
    جات
    -0.06
     LANGUAGE
    -0.06
    .Clone
    -0.06
     trainable
    -0.06
    尾
    -0.06
     hug
    -0.06
    POSITIVE LOGITS
     SECRET
    0.06
    JI
    0.06
    氧
    0.06
    >?
    0.06
    console
    0.06
    /stretchr
    0.06
    νομ
    0.06
    ;top
    0.06
     nitelik
    0.06
     истор
    0.06
    Act Density 0.007%

    No Known Activations