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

    Neuronpedia

    INDEX
    Explanations

    key terms related to research findings and statistical significance

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

    major limitations, approaches, contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.41
    </strong>
    -0.40
    readAs
    -0.37
    </blockquote>
    -0.37
    //
    -0.34
     pernas
    -0.33
    </em>
    -0.33
     obro
    -0.32
    พิ
    -0.31
     Til
    -0.31
    POSITIVE LOGITS
    AnchorStyles
    0.60
     CreateTagHelper
    0.57
     تضيفلها
    0.56
    LabelTagHelper
    0.56
    DebuggerNonUser
    0.55
    KURZBESCHREIBUNG
    0.51
    archiviato
    0.50
    setVerticalGroup
    0.49
    AndEndTag
    0.49
    tonsoft
    0.47
    Act Density 0.095%

    No Known Activations