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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adhesive
    -0.07
     mobility
    -0.07
    Entry
    -0.06
     Although
    -0.06
    .DataGridViewColumn
    -0.06
    Station
    -0.06
    64
    -0.06
    ková
    -0.06
     Palestin
    -0.06
    .gmail
    -0.06
    POSITIVE LOGITS
    يات
    0.06
    にお
    0.06
     fors
    0.06
    �
    0.06
    inte
    0.06
    itte
    0.06
    emodel
    0.06
     ΑΠ
    0.06
    .chat
    0.06
    âng
    0.06
    Act Density 0.256%

    No Known Activations