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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions related to concern and distress

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

    negative words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.64
    #+#
    -0.59
     Administrativna
    -0.57
    Personendaten
    -0.56
    tagHelperRunner
    -0.53
    aarrggbb
    -0.52
    ftagPool
    -0.47
    ⟬
    -0.47
    艋
    -0.47
     Einfluß
    -0.46
    POSITIVE LOGITS
    UserScript
    0.42
    Jeografia
    0.39
    不怕
    0.37
    koneksi
    0.33
     Mix
    0.33
    Síguenos
    0.32
    FieldDescriptor
    0.31
     Kons
    0.31
     Levi
    0.31
    ARA
    0.31
    Act Density 0.823%

    No Known Activations