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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yar
    -0.07
    Incoming
    -0.07
     savings
    -0.07
    usat
    -0.06
     ANC
    -0.06
    _nested
    -0.06
    traffic
    -0.06
    جر
    -0.06
    .Collections
    -0.06
     ions
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.08
    (""));↵
    0.06
    voke
    0.06
    tridges
    0.06
    CallableWrapper
    0.06
    )↵↵↵↵↵↵↵↵
    0.06
    -dismissible
    0.06
    кувати
    0.06
     Despite
    0.06
    ":
↵
    0.06
    Act Density 0.001%

    No Known Activations