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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron activates on strong swear words and obscene profanities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     revenge
    -0.07
     Plan
    -0.07
     newNode
    -0.07
    STALL
    -0.06
     أمر
    -0.06
     report
    -0.06
     Owners
    -0.06
     poison
    -0.06
    .Disabled
    -0.06
     Therapy
    -0.06
    POSITIVE LOGITS
     καθ
    0.07
     \'
    0.07
    ‌های
    0.07
    ůj
    0.07
     Upload
    0.07
    getInt
    0.07
     Forums
    0.06
    .it
    0.06
    อดภ
    0.06
    ($('#
    0.06
    Act Density 0.009%

    No Known Activations