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

    Neuronpedia

    INDEX
    Explanations

    references to tools or resources

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

    toolbox or toolkit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \,
    -0.39
    <blockquote>
    -0.38
     Burgen
    -0.37
     sas
    -0.36
     stra
    -0.36
    ($"
    -0.35
    bukkit
    -0.34
     có
    -0.34
    addEvent
    -0.34
    <h2>
    -0.34
    POSITIVE LOGITS
    toolbox
    1.98
     toolbox
    1.22
    Toolbox
    1.21
     Toolbox
    1.20
     kasarigan
    0.75
     Roskov
    0.69
     herramienta
    0.65
     Numerade
    0.64
     ferramentas
    0.63
     toolkit
    0.62
    Act Density 0.000%

    No Known Activations