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

    Neuronpedia

    INDEX
    Explanations

    references to class or object identifiers in programming contexts

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

    names, contact info, and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.49
    Посилання
    -0.41
     comfy
    -0.39
    ⓧ
    -0.38
    ソッド
    -0.38
    ására
    -0.37
     menudo
    -0.37
    Tikang
    -0.35
     дописавши
    -0.35
    χι
    -0.34
    POSITIVE LOGITS
    +#+
    0.55
    stdc
    0.52
     GenerationType
    0.49
    GenerationType
    0.48
    atorics
    0.48
    ngths
    0.47
    protoimpl
    0.47
    SBATCH
    0.47
    ñera
    0.46
    ricians
    0.46
    Act Density 0.002%

    No Known Activations