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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and functions within programming languages

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

    code or markup attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.68
     հղումներ
    -0.60
     transfieras
    -0.59
    +:+
    -0.53
     للاسماء
    -0.50
    BagConstraints
    -0.50
     iprot
    -0.49
    AndEndTag
    -0.49
    glTexCoord
    -0.48
    帖最后由
    -0.48
    POSITIVE LOGITS
     defaultstate
    0.52
     politiet
    0.47
    berdayakan
    0.46
     tradizionale
    0.41
     tradisional
    0.40
     traditionnel
    0.40
     traditionnels
    0.40
    épendant
    0.40
     čierna
    0.39
    ритори
    0.39
    Act Density 0.016%

    No Known Activations