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

    Neuronpedia

    INDEX
    Explanations

    my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Powder
    -0.07
    Slider
    -0.06
    �
    -0.06
    托
    -0.06
     Drinking
    -0.06
    srv
    -0.06
    Stay
    -0.06
    acio
    -0.06
    (padding
    -0.06
    Define
    -0.06
    POSITIVE LOGITS
    }`}>↵
    0.07
    �
    0.06
     writeFile
    0.06
     εγκα
    0.06
    дии
    0.06
    Mit
    0.06
     уд
    0.06
    _Test
    0.06
     свеж
    0.06
    穿
    0.06
    Act Density 0.044%

    No Known Activations