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

    Neuronpedia

    INDEX
    Explanations

    spin

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the root “spin” (e.g. “spin,” “spinning,” “spun,” “spin-up,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    kých
    -0.08
    artment
    -0.07
     každé
    -0.07
     leakage
    -0.07
    	Rect
    -0.07
     Welfare
    -0.07
     Kathy
    -0.07
     McCart
    -0.07
     MCC
    -0.06
     lodge
    -0.06
    POSITIVE LOGITS
     spin
    0.13
     Spin
    0.12
     spun
    0.11
    Spin
    0.11
    spin
    0.10
     spinning
    0.10
     spins
    0.10
    IN
    0.09
    in
    0.09
    INS
    0.08
    Act Density 0.007%

    No Known Activations