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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moi
    -0.08
    Gun
    -0.07
    Ly
    -0.07
    ullets
    -0.06
    STRACT
    -0.06
    FIT
    -0.06
     contribute
    -0.06
    IBUT
    -0.06
    支
    -0.06
    _variation
    -0.06
    POSITIVE LOGITS
    以下简称
    0.07
    景德镇
    0.07
     conven
    0.06
    _REPLACE
    0.06
    _ENUM
    0.06
    空调
    0.06
     Fresno
    0.06
    اجتماع
    0.06
     Interpreter
    0.06
     피해
    0.06
    Act Density 0.028%

    No Known Activations