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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles associated with legal cases

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

    company and proper names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grundlagen
    -0.36
     Städten
    -0.33
     Ursache
    -0.33
     Küste
    -0.31
     justement
    -0.31
     Varianten
    -0.31
     claramente
    -0.30
     biasa
    -0.29
     Dafür
    -0.29
     Voraussetzungen
    -0.29
    POSITIVE LOGITS
    <unused8>
    1.05
    <unused3>
    1.04
    <unused23>
    1.04
    <unused47>
    1.04
    <unused51>
    1.04
    [@BOS@]
    1.04
    <unused14>
    1.04
    <unused41>
    1.04
    <unused74>
    1.04
    <unused28>
    1.04
    Act Density 0.030%

    No Known Activations