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

    Neuronpedia

    INDEX
    Explanations

    narrative styles of polite humor with a focus on social observations.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    refusal and cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     irrespective
    0.34
     degraded
    0.33
     Lik
    0.33
     with
    0.31
    alities
    0.30
     IDs
    0.29
     localities
    0.29
     subdivided
    0.29
     Vi
    0.28
     Is
    0.28
    POSITIVE LOGITS
    ऊदी
    0.37
     verificare
    0.35
    𒆳
    0.35
    <unused1043>
    0.34
     faptul
    0.33
    േജ്
    0.33
    nota
    0.33
     proveedor
    0.33
     imen
    0.33
     Eriksson
    0.33
    Act Density 0.296%

    No Known Activations