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

    Neuronpedia

    INDEX
    Explanations

    Names from email exchanges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDE
    -0.07
    rip
    -0.07
    Guard
    -0.06
    UNS
    -0.06
     MCP
    -0.06
     Lucifer
    -0.06
    腐
    -0.06
     tendon
    -0.06
    /editor
    -0.06
     Cardio
    -0.06
    POSITIVE LOGITS
     Milf
    0.07
    .getBytes
    0.07
     authored
    0.07
     ];
    0.06
     ofApp
    0.06
     allied
    0.06
    主义
    0.06
    vě
    0.06
    _ck
    0.06
    _insn
    0.06
    Act Density 0.014%

    No Known Activations