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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    girl
    0.46
    another
    0.44
    '][:
    0.42
     паке
    0.40
    мих
    0.40
    Girl
    0.39
    ತಿ
    0.39
    িসহ
    0.39
    Otra
    0.38
    }({\
    0.38
    POSITIVE LOGITS
     from
    0.44
     contro
    0.41
     Permissions
    0.40
     ร
    0.38
     Yup
    0.38
     fus
    0.38
     R
    0.37
     από
    0.37
     từ
    0.36
     dotenv
    0.36
    Act Density 0.000%

    No Known Activations