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

    Neuronpedia

    INDEX
    Explanations

    actions or instructions related to completing tasks

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

    completing tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jedis
    -0.37
    MENAFN
    -0.35
    DockStyle
    -0.35
    öh
    -0.34
    makeConstraints
    -0.34
    利
    -0.33
    localVar
    -0.33
    の
    -0.33
     못
    -0.32
    bootstrapcdn
    -0.32
    POSITIVE LOGITS
     Autorizaciones
    0.60
    AndEndTag
    0.59
     ſehr
    0.59
    ⤹
    0.54
    featureID
    0.53
     Geſch
    0.52
     itſelf
    0.52
     Waſſer
    0.51
    ⟬
    0.50
     CreateTagHelper
    0.50
    Act Density 0.072%

    No Known Activations