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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    killer
    -0.09
    $category
    -0.08
    equalTo
    -0.07
     Helen
    -0.07
    .fxml
    -0.07
    τικα
    -0.06
     vše
    -0.06
    "..
    -0.06
    genres
    -0.06
     škol
    -0.06
    POSITIVE LOGITS
    [P
    0.07
     　 　 　 　 　 　
    0.07
    spec
    0.07
    ัมพ
    0.06
    ซ
    0.06
    .Completed
    0.06
    (L
    0.06
    (coll
    0.06
     Milwaukee
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations