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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detected
    -0.06
     Consulting
    -0.06
     occup
    -0.06
     Songs
    -0.06
    	AT
    -0.06
     Lou
    -0.06
     �
    -0.06
     Diane
    -0.06
     Python
    -0.06
    .goods
    -0.06
    POSITIVE LOGITS
    ляються
    0.07
    専
    0.06
     Mustang
    0.06
     هستند
    0.06
     Flynn
    0.06
    -session
    0.06
    ι
    0.06
     KG
    0.06
    intl
    0.06
     підприємства
    0.06
    Act Density 0.000%

    No Known Activations