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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of research study design and methodology (e.g. “prospective,” “randomized,” “comparative study,” “trial,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    觉得
    -0.06
    üle
    -0.06
    _acquire
    -0.06
    hunt
    -0.06
    hooks
    -0.06
    .mem
    -0.06
    inds
    -0.06
    .Tick
    -0.06
     Tart
    -0.06
    (Roles
    -0.06
    POSITIVE LOGITS
    直接
    0.07
    Century
    0.07
    164
    0.06
     Melee
    0.06
    ็อต
    0.06
     Super
    0.06
    ]){
    0.06
    ernational
    0.06
    StringRef
    0.06
    ael
    0.06
    Act Density 0.020%

    No Known Activations