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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hrá
    -0.07
    ديث
    -0.06
    Installer
    -0.06
    メージ
    -0.06
     işlet
    -0.06
    *>(&
    -0.06
    ラック
    -0.06
     councillor
    -0.06
    trfs
    -0.06
     vů
    -0.06
    POSITIVE LOGITS
    .sidebar
    0.07
    .components
    0.07
    uation
    0.06
    ências
    0.06
    essential
    0.06
    probably
    0.06
     Behavior
    0.06
    full
    0.06
     probably
    0.06
    账
    0.06
    Act Density 0.662%

    No Known Activations