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

    Neuronpedia

    INDEX
    Explanations

    safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Current
    -0.07
     см
    -0.07
     incorporation
    -0.07
    (api
    -0.07
    ιστο
    -0.07
    izzes
    -0.06
     зараз
    -0.06
    ádu
    -0.06
    히
    -0.06
    -bel
    -0.06
    POSITIVE LOGITS
    994
    0.06
    rası
    0.06
    .optimizer
    0.06
    .Logger
    0.06
     odkazy
    0.06
     позволя
    0.06
    QPushButton
    0.06
    ž
    0.06
     Caleb
    0.06
     waterfront
    0.06
    Act Density 0.014%

    No Known Activations