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

    Neuronpedia

    INDEX
    Explanations

    the presence of string data types and related elements in code

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

    string variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unilaterally
    -0.44
     unilateral
    -0.38
    AutoScale
    -0.37
     HasFactory
    -0.37
    rinology
    -0.37
     preceded
    -0.35
     jerawat
    -0.34
     Übernach
    -0.33
     delivered
    -0.33
     disprove
    -0.32
    POSITIVE LOGITS
    Autoritní
    0.68
    Personendaten
    0.61
    +#+
    0.57
     Roskov
    0.56
    extAlignment
    0.55
    évaluateur
    0.53
    aarrggbb
    0.52
    0.52
    opsida
    0.52
    脚注の使い方
    0.48
    Act Density 0.002%

    No Known Activations