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

    Neuronpedia

    INDEX
    Explanations

    specific programming or structural elements used in code

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

    this user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bezpieczeństwa
    -0.42
     açıklama
    -0.39
     Melton
    -0.37
     dolayı
    -0.36
     Worten
    -0.36
     cumbre
    -0.35
     redonda
    -0.35
     treble
    -0.34
    ühlen
    -0.34
     dilihat
    -0.33
    POSITIVE LOGITS
    OLEAN
    0.55
     Roskov
    0.54
     يتيمه
    0.53
    RTHOOK
    0.53
    RTLU
    0.51
    twimg
    0.50
    Autoritní
    0.49
    CppMethod
    0.49
    RTLR
    0.48
    RTSC
    0.47
    Act Density 0.001%

    No Known Activations