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

    Neuronpedia

    INDEX
    Explanations

    actions or events occurring in specific locations

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

    actions followed by completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.61
     disambiguazione
    -0.60
     Numerade
    -0.59
     ujednoznacz
    -0.58
    ConstraintMaker
    -0.57
    ThroughAttribute
    -0.56
     للمعارف
    -0.56
     Италијани
    -0.56
    الدراسه
    -0.53
     الرياضيه
    -0.53
    POSITIVE LOGITS
    ().__
    0.36
    zium
    0.35
    })();
    0.34
    woofer
    0.33
     planned
    0.33
    Története
    0.33
    Absent
    0.32
     pul
    0.32
    expandindo
    0.32
    つもり
    0.31
    Act Density 0.064%

    No Known Activations