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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิด
    -0.07
    .cwd
    -0.07
    <long
    -0.06
     obsessed
    -0.06
     fica
    -0.06
     Т
    -0.06
    aturday
    -0.06
     DAG
    -0.06
     famed
    -0.06
    ıb
    -0.06
    POSITIVE LOGITS
    geber
    0.07
    istes
    0.07
    decision
    0.06
    469
    0.06
     الموس
    0.06
     firmware
    0.06
    annabin
    0.06
    extras
    0.06
    liğinde
    0.06
    ListView
    0.06
    Act Density 0.005%

    No Known Activations