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

    Neuronpedia

    INDEX
    Explanations

    bad

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on occurrences of “Breaking Bad,” i.e. it detects mentions of the TV series title.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ople
    -0.07
    swiper
    -0.07
    .credit
    -0.06
    .angle
    -0.06
    
    -0.06
     Humph
    -0.06
    /frame
    -0.06
    ／/
    -0.06
    /Button
    -0.06
    ویل
    -0.06
    POSITIVE LOGITS
     Dad
    0.07
     第三
    0.06
     ناح
    0.06
     Sa
    0.06
     $('.
    0.06
     [↵
    0.06
    йн
    0.06
    OnInit
    0.06
     interim
    0.06
    .setIcon
    0.06
    Act Density 0.002%

    No Known Activations