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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Adapter
    -0.07
     Desde
    -0.07
    [S
    -0.07
     MaterialApp
    -0.07
     helmet
    -0.06
     swal
    -0.06
     isempty
    -0.06
    อำเภ
    -0.06
    �
    -0.06
     בבק
    -0.06
    POSITIVE LOGITS
    基础
    0.07
     earlier
    0.07
     Hob
    0.07
    货币
    0.07
     maps
    0.07
    Charge
    0.07
    Plan
    0.07
    BS
    0.07
     fury
    0.07
    ă
    0.07
    Act Density 0.211%

    No Known Activations