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

    Neuronpedia

    INDEX
    Explanations

    Teamwork and reflection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーム
    -0.06
     Baptist
    -0.06
    ],"
    -0.06
    ext
    -0.06
    _texts
    -0.06
    pression
    -0.06
    .sync
    -0.06
     Escape
    -0.06
     facts
    -0.06
     slips
    -0.06
    POSITIVE LOGITS
     unequiv
    0.08
     Juli
    0.07
     rotterdam
    0.07
    (instr
    0.07
    ẳ
    0.06
    oxetine
    0.06
    _answer
    0.06
     an
    0.06
     hike
    0.06
    (Bit
    0.06
    Act Density 0.083%

    No Known Activations