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

    Neuronpedia

    INDEX
    Explanations

    references to conditional or hypothetical situations

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

    prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.54
    ⟬
    -0.52
     ddelweddau
    -0.52
    IntoConstraints
    -0.47
     pleaſure
    -0.47
     Wicidata
    -0.47
     ſol
    -0.46
     propOrder
    -0.45
    uidado
    -0.45
     IndexPath
    -0.45
    POSITIVE LOGITS
    omiast
    0.37
     upang
    0.37
     ffilmiau
    0.36
     sputum
    0.36
    RepeatedField
    0.35
    ———
    0.35
    rospy
    0.35
     desertcart
    0.35
    Obra
    0.34
    vtx
    0.34
    Act Density 0.393%

    No Known Activations