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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nac
    -0.08
    sar
    -0.08
    ોએ
    -0.08
     Edgar
    -0.08
     Moor
    -0.08
     reimbursement
    -0.08
     kuwo
    -0.07
     CARD
    -0.07
     Kod
    -0.07
     আরও
    -0.07
    POSITIVE LOGITS
    -than
    0.14
     allá
    0.12
    _than
    0.12
    ाधिक
    0.12
    Than
    0.12
     than
    0.10
    तम
    0.09
     বেশি
    0.09
    _THAN
    0.09
     importantly
    0.09
    Act Density 0.126%

    No Known Activations