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

    Neuronpedia

    INDEX
    Explanations

    technical data related to experimental procedures and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    temperature and speed gradients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    shop
    -0.43
    desert
    -0.42
     desert
    -0.40
    ⟬
    -0.40
    Tikang
    -0.40
    nash
    -0.39
    ">//
    -0.38
    OGND
    -0.38
    eras
    -0.37
     Desert
    -0.36
    POSITIVE LOGITS
    prefixer
    0.51
    routeProvider
    0.48
     temperatures
    0.47
     temperature
    0.46
     programmatic
    0.46
     policiales
    0.45
    beforeAll
    0.44
     judiciales
    0.43
    ayuno
    0.43
     ramping
    0.43
    Act Density 0.149%

    No Known Activations