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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge sharing and guidance

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

    sharing valuable advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    recated
    -0.52
     Taktlose
    -0.51
     tartalomajánló
    -0.50
     مشين
    -0.48
     noDo
    -0.47
     transfieras
    -0.46
    CrossRef
    -0.46
     Photocase
    -0.46
    OGND
    -0.46
    afficheront
    -0.46
    POSITIVE LOGITS
     valuable
    0.63
     gleaned
    0.60
     invaluable
    0.58
    valuable
    0.55
     précieux
    0.54
     priceless
    0.52
     précie
    0.51
     insights
    0.50
     helpful
    0.50
     imparted
    0.49
    Act Density 0.026%

    No Known Activations