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

    Neuronpedia

    INDEX
    Explanations

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    striped
    1.24
    ili
    1.23
     EMPLOY
    1.23
    questions
    1.22
     ntawm
    1.22
    ƙ
    1.22
    erp
    1.21
    starred
    1.21
    espa
    1.20
    southeast
    1.17
    POSITIVE LOGITS
    ння
    1.42
    ת
    1.42
    عه
    1.41
    不高
    1.39
    ਾ
    1.38
    า
    1.37
    га
    1.36
     surfactant
    1.34
    ру
    1.34
     وطالبات
    1.34
    Act Density 0.011%

    No Known Activations