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

    Neuronpedia

    INDEX
    Explanations

    online forum excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oscars
    -0.07
    "When
    -0.07
    Star
    -0.06
     tents
    -0.06
    "Do
    -0.06
     Otherwise
    -0.06
     �
    -0.06
    (pad
    -0.06
    “When
    -0.06
     quienes
    -0.06
    POSITIVE LOGITS
    LOY
    0.07
    pector
    0.07
     Tropical
    0.07
    _update
    0.07
    ayout
    0.06
     Vegetable
    0.06
     whatever
    0.06
    ню
    0.06
     Sinatra
    0.06
    -groups
    0.06
    Act Density 0.003%

    No Known Activations