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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and identifiers related to names and items

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

    Alexandria, clientId, Petersburg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rotor
    -0.40
    findpost
    -0.38
    ifrance
    -0.37
     Jalisco
    -0.36
    出
    -0.35
     Rptr
    -0.35
    被
    -0.34
     inggris
    -0.34
    Porsche
    -0.33
    Hitler
    -0.33
    POSITIVE LOGITS
     Alexandria
    2.14
    Alexandria
    1.99
    andria
    1.34
     Alexand
    1.00
    Alexand
    0.90
     Александ
    0.76
    angelo
    0.74
    Datuak
    0.68
     Alexandra
    0.67
    Portály
    0.67
    Act Density 0.001%

    No Known Activations