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

    Neuronpedia

    INDEX
    Explanations

    Hiding feelings

    np_max-act · gemini-2.0-flash

    The neuron does not respond to any tokens—it remains inactive.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ==============
    -0.07
    див
    -0.06
    [u
    -0.06
    頭
    -0.06
     captcha
    -0.06
     скор
    -0.06
    头
    -0.06
    sharp
    -0.06
     Lois
    -0.06
    Calls
    -0.06
    POSITIVE LOGITS
     partly
    0.07
     panicked
    0.07
     쪽
    0.07
     Turing
    0.06
     ارزیابی
    0.06
    realDonaldTrump
    0.06
     manages
    0.06
     Carnival
    0.06
    dehyde
    0.06
     روش
    0.06
    Act Density 0.020%

    No Known Activations