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

    Neuronpedia

    INDEX
    Explanations

    references to positions or orientations in a spatial context

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

    top, back, bottom locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.50
     nepř
    -0.45
     bieden
    -0.45
    Véxase
    -0.45
     podp
    -0.44
    Geplaatst
    -0.42
     varandra
    -0.42
     balcón
    -0.41
    relativeTime
    -0.40
     sonriente
    -0.40
    POSITIVE LOGITS
     esternos
    0.68
    InputBorder
    0.61
    ymce
    0.59
     estekak
    0.56
    OnTop
    0.55
    PerformLayout
    0.52
    httphttps
    0.52
    الحياه
    0.50
    GOTREF
    0.50
    jspb
    0.48
    Act Density 0.036%

    No Known Activations