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

    Neuronpedia

    INDEX
    Explanations

    stick

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the verb phrase “stick to” (as in “stick to X”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ample
    -0.07
     فراهم
    -0.07
     Age
    -0.07
    атів
    -0.07
    RF
    -0.07
     Early
    -0.07
    altung
    -0.06
    World
    -0.06
    ORLD
    -0.06
     NRF
    -0.06
    POSITIVE LOGITS
     stick
    0.16
     Stick
    0.14
     sticks
    0.12
    stick
    0.11
    Stick
    0.11
     stuck
    0.10
     sticking
    0.10
    pick
    0.10
     Sticky
    0.08
     poking
    0.08
    Act Density 0.009%

    No Known Activations