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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ignoring
    -0.06
    .res
    -0.06
    身
    -0.06
    tures
    -0.06
     decir
    -0.06
    contents
    -0.06
    came
    -0.06
    ενοδο
    -0.06
    ActionResult
    -0.06
    ервые
    -0.06
    POSITIVE LOGITS
     مهم
    0.08
     �
    0.07
     minecraft
    0.07
     nuis
    0.07
     حض
    0.06
     enforce
    0.06
     तस
    0.06
     Willie
    0.06
     Blick
    0.06
    .vote
    0.06
    Act Density 0.057%

    No Known Activations