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

    Neuronpedia

    INDEX
    Explanations

    online watching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    match
    -0.08
     cabbage
    -0.07
     salad
    -0.07
    드로
    -0.07
    acro
    -0.07
    zers
    -0.07
     videog
    -0.07
     Expand
    -0.07
     Salad
    -0.07
     طی
    -0.07
    POSITIVE LOGITS
    �
    0.06
    �
    0.06
    .Offset
    0.06
    ชาว
    0.06
     міг
    0.06
     NoSuch
    0.06
     žal
    0.06
     tuberculosis
    0.06
    щина
    0.06
    (fontSize
    0.05
    Act Density 0.031%

    No Known Activations