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

    Neuronpedia

    INDEX
    Explanations

    alternatives and additions

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of offering non‐spicy food options (e.g. “offer some non-spicy food”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     curse
    -0.06
     rast
    -0.06
    Authorities
    -0.06
     和
    -0.06
    .SelectedItems
    -0.06
    GetData
    -0.06
     colleagues
    -0.06
    (".");↵
    -0.06
     synth
    -0.06
     printers
    -0.06
    POSITIVE LOGITS
    ={↵
    0.07
     concentrating
    0.06
    €™
    0.06
     اقتصادی
    0.06
    αλλ
    0.06
     Documentation
    0.06
     développement
    0.06
    uptime
    0.06
    ::::|
    0.06
     شخص
    0.06
    Act Density 0.019%

    No Known Activations