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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "all."

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

    this all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    angliski
    -0.42
     MATHEMATICAL
    -0.40
     polaire
    -0.40
     MATRIX
    -0.38
     practitioners
    -0.38
     referenties
    -0.38
    قایناق‌لار
    -0.38
    WithFormat
    -0.38
    Helvetica
    -0.38
     prisons
    -0.36
    POSITIVE LOGITS
     متعلقه
    0.51
    MENAFN
    0.50
     leider
    0.49
     otomatig
    0.47
    ioutil
    0.47
     sadly
    0.47
    complexContent
    0.47
    Aktualisiert
    0.46
    bygg
    0.45
    Еще
    0.45
    Act Density 0.007%

    No Known Activations