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

    Neuronpedia

    INDEX
    Explanations

    quantities or degrees of certainty and belief

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

    expressing opinions or beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intervento
    -0.45
     Hilfe
    -0.42
     Nutzung
    -0.41
     Wirkungen
    -0.41
     cuisson
    -0.41
     Ruhe
    -0.38
     cuidar
    -0.38
    原始内容存档于
    -0.38
     Atlántico
    -0.38
     Qualität
    -0.38
    POSITIVE LOGITS
     belief
    0.59
    windowFixed
    0.56
     hypothe
    0.54
     faptul
    0.52
     believe
    0.52
    assertRaises
    0.51
    enumii
    0.50
     suppose
    0.50
     guess
    0.49
     possibility
    0.49
    Act Density 0.063%

    No Known Activations