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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is pick up references to physical conflict or combat actions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     مالی
    -0.07
     tahun
    -0.07
     sponsored
    -0.07
    Jos
    -0.07
     врач
    -0.06
    nst
    -0.06
    Profiles
    -0.06
    λλ
    -0.06
    .ObjectMapper
    -0.06
    uetooth
    -0.06
    POSITIVE LOGITS
    "",↵
    0.07
     churn
    0.06
     Všech
    0.06
     hyster
    0.06
     Tabs
    0.06
     cif
    0.06
     fearless
    0.06
    ""↵
    0.06
    hya
    0.06
     shares
    0.06
    Act Density 0.020%

    No Known Activations