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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chair
    -0.06
    _LOC
    -0.06
     اسلام
    -0.06
     unanim
    -0.06
    「お
    -0.06
     New
    -0.06
     Principal
    -0.06
    endsWith
    -0.06
     /*
↵
    -0.06
    Có
    -0.06
    POSITIVE LOGITS
     fibonacci
    0.08
    erno
    0.07
     GWei
    0.07
     حالت
    0.07
     sik
    0.06
    regon
    0.06
     chrom
    0.06
     cleaner
    0.06
    quiv
    0.06
    kelig
    0.06
    Act Density 0.000%

    No Known Activations