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

    Neuronpedia

    INDEX
    Explanations

    approach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rgb
    -0.06
     راهنم
    -0.06
    manager
    -0.06
     dinners
    -0.06
    ふ
    -0.06
     guessing
    -0.06
    :${
    -0.06
    -manager
    -0.06
     chaud
    -0.06
    -password
    -0.06
    POSITIVE LOGITS
    tí
    0.07
    Cong
    0.07
    _Act
    0.07
     offensive
    0.06
     Congress
    0.06
    �
    0.06
     undercover
    0.06
    Ì
    0.06
     Dut
    0.06
     movable
    0.06
    Act Density 0.005%

    No Known Activations