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

    Neuronpedia

    INDEX
    Explanations

    feedback

    np_max-act · gemini-2.0-flash

    Mentions of feedback—especially feedback loops or iterative feedback mechanisms.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     Trong
    -0.08
    “There
    -0.08
    					
↵
    -0.07
    "There
    -0.07
    th
    -0.07
     cosine
    -0.07
     row
    -0.07
    -0.06
     cat
    -0.06
    /article
    -0.06
    POSITIVE LOGITS
     feedback
    0.09
     Feedback
    0.08
    Feedback
    0.07
    feedback
    0.07
     cảm
    0.07
    essaging
    0.06
     fk
    0.06
     Taliban
    0.06
    fv
    0.06
     Pek
    0.06
    Act Density 0.006%

    No Known Activations