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

    Neuronpedia

    INDEX
    Explanations

    cycle

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of “cell cycle” (e.g. in phrases like cell cycle arrest or progression).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ihilation
    -0.07
     micro
    -0.07
    >t
    -0.07
     plant
    -0.06
     pollen
    -0.06
     cat
    -0.06
    _strdup
    -0.06
     बल
    -0.06
     lParam
    -0.06
     Mas
    -0.06
    POSITIVE LOGITS
    utes
    0.08
     resized
    0.07
    ]:=
    0.07
    Until
    0.07
     */↵↵
    0.06
    Making
    0.06
    0.06
    <div
    0.06
    UTES
    0.06
     noisy
    0.06
    Act Density 0.002%

    No Known Activations