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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on phrases that describe thorough, detailed tactile exploration—especially constructions like “exploring every inch of (someone’s body).”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    480
    -0.07
    severity
    -0.07
    gold
    -0.07
     Logging
    -0.07
     Zion
    -0.07
     Mund
    -0.06
    falls
    -0.06
    vara
    -0.06
     Lace
    -0.06
     fences
    -0.06
    POSITIVE LOGITS
    ریق
    0.06
    .setWidth
    0.06
    SectionsIn
    0.06
     crem
    0.06
    (begin
    0.06
     ether
    0.06
     blended
    0.06
     authService
    0.06
    ){//
    0.06
    .arg
    0.05
    Act Density 0.005%

    No Known Activations