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

    Neuronpedia

    INDEX
    Explanations

    specifications concerning visual attributes and programming constructs

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

    key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.83
     verſch
    -0.63
    Демографія
    -0.59
     autorytatywna
    -0.59
     laſſen
    -0.59
    IsMutable
    -0.57
    AsUp
    -0.56
     increí
    -0.55
     propOrder
    -0.54
     wireType
    -0.54
    POSITIVE LOGITS
    CrossRef
    0.41
    Crossref
    0.37
    oken
    0.37
    angor
    0.36
    DECREF
    0.34
     बु
    0.33
     sop
    0.32
     gema
    0.32
    token
    0.31
    natural
    0.31
    Act Density 0.055%

    No Known Activations