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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tro
    -0.07
    Ta
    -0.07
     parted
    -0.06
    Loc
    -0.06
     scrut
    -0.06
     propriet
    -0.06
    _da
    -0.06
     лей
    -0.06
     trop
    -0.06
     économ
    -0.06
    POSITIVE LOGITS
     nghiệm
    0.07
     [$
    0.07
    boo
    0.07
    หาก
    0.07
    初
    0.07
    ‌هایی
    0.06
     içer
    0.06
     unicorn
    0.06
    	stream
    0.06
    .badlogic
    0.06
    Act Density 0.052%

    No Known Activations