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

    Neuronpedia

    INDEX
    Explanations

    Software Licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ܫ
    -0.07
    🅖
    -0.07
    ⌡
    -0.07
    innitus
    -0.06
     Crazy
    -0.06
    	me
    -0.06
    �
    -0.06
    נהג
    -0.06
    人体
    -0.06
    𬜯
    -0.06
    POSITIVE LOGITS
     kicked
    0.07
     {}\
    0.07
     alleles
    0.07
     excluded
    0.07
     isSuccess
    0.07
    ሉ
    0.07
    丰硕
    0.07
     waived
    0.07
     Jacques
    0.07
     talked
    0.06
    Act Density 0.003%

    No Known Activations