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

    Neuronpedia

    INDEX
    Explanations

    lines of code or programming constructs

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

    stack trace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.77
    ⟬
    -0.57
    HostException
    -0.55
    Clik
    -0.53
    HasAnnotation
    -0.51
    ValueStyle
    -0.50
     purpoſe
    -0.47
    saraba
    -0.47
     ſte
    -0.47
    JspWriter
    -0.46
    POSITIVE LOGITS
    Tikang
    0.45
    putan
    0.44
    uxxxx
    0.42
     vêtement
    0.41
    Démographie
    0.41
     procédé
    0.38
     necessários
    0.37
     potência
    0.36
    Personendaten
    0.36
     initial
    0.35
    Act Density 0.018%

    No Known Activations