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

    Neuronpedia

    INDEX
    Explanations

    question marks followed by ampersands, or the word "the".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erotik
    -0.09
     nackte
    -0.09
     eskort
    -0.07
    iyim
    -0.07
     Kostenlose
    -0.07
    icho
    -0.07
     Kostenlos
    -0.06
     Datensch
    -0.06
     huku
    -0.06
     Kash
    -0.06
    POSITIVE LOGITS
    Ñī
    0.06
     èģĶ
    0.06
    forman
    0.06
    -ÑĤо
    0.06
    ertype
    0.05
    ubb
    0.05
     subdiv
    0.05
     tesis
    0.05
    ãĥ³ãĤº
    0.05
    dbg
    0.05
    Act Density 0.204%

    No Known Activations