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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Qatar
    -0.07
    ران
    -0.06
     adlandır
    -0.06
     करत
    -0.06
    有人
    -0.06
    nam
    -0.06
    苏
    -0.06
     intest
    -0.06
     recal
    -0.06
    έργ
    -0.06
    POSITIVE LOGITS
     Jahren
    0.06
    ennes
    0.06
    type
    0.06
    WEEN
    0.06
    iden
    0.06
    orious
    0.06
     assembler
    0.06
     mediums
    0.06
    TP
    0.06
    ibile
    0.06
    Act Density 0.020%

    No Known Activations