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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating uncertainty or the potential for future events

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

    distant or elusive goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.56
     snippetHide
    -0.55
     otomatig
    -0.54
     ब्रेकडाउन
    -0.53
    ņi
    -0.49
    MemoryWarning
    -0.48
     محفوظة
    -0.45
     HasFactory
    -0.45
    abestanden
    -0.44
    principalColumn
    -0.44
    POSITIVE LOGITS
    reality
    0.47
     Strain
    0.47
     aspir
    0.47
    aspir
    0.45
    Strain
    0.45
     aspiration
    0.44
    dream
    0.43
     attainable
    0.43
    Reality
    0.42
     unat
    0.41
    Act Density 0.089%

    No Known Activations