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

    Neuronpedia

    INDEX
    Explanations

    to start

    np_max-act · gemini-2.0-flash

    This neuron activates on phrasing that signals getting off to or having a strong “start,” especially the idiom “off to a good start.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wines
    -0.08
     Mits
    -0.06
    íř
    -0.06
    _https
    -0.06
     drain
    -0.06
     Evangel
    -0.06
    udur
    -0.06
    urers
    -0.06
     Rage
    -0.06
     Sid
    -0.06
    POSITIVE LOGITS
    초등학교
    0.08
     відкрит
    0.07
    "+"
    0.07
     판매
    0.07
     enfermed
    0.06
    lick
    0.06
    [mask
    0.06
    τύ
    0.06
     RECEIVE
    0.06
    ">↵↵
    0.06
    Act Density 0.011%

    No Known Activations