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

    Neuronpedia

    INDEX
    Explanations

    limits and maximums

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the model’s input‐length or token‐limit capabilities and related guidance on conciseness.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <y
    -0.06
    ğim
    -0.06
     SEE
    -0.06
     indeed
    -0.06
    woff
    -0.06
    Blockly
    -0.06
     meziná
    -0.06
    ;';↵
    -0.06
     interpersonal
    -0.06
    itial
    -0.06
    POSITIVE LOGITS
     Celebr
    0.07
    ]=(
    0.07
    Weapons
    0.06
     perí
    0.06
    建築
    0.06
     vd
    0.06
     resemblance
    0.06
    Angles
    0.06
     verir
    0.06
    dí
    0.06
    Act Density 0.034%

    No Known Activations