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

    Neuronpedia

    INDEX
    Explanations

    politics and media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PUT
    -0.07
     exhibited
    -0.07
    _)
    -0.07
    (py
    -0.07
     latter
    -0.07
     explaining
    -0.07
    .\"
    -0.06
     nothing
    -0.06
    というもの
    -0.06
    อาจจะ
    -0.06
    POSITIVE LOGITS
    驺
    0.08
     bloom
    0.07
     Norris
    0.07
    慎
    0.07
    💐
    0.07
    *sizeof
    0.07
     direccion
    0.07
    iping
    0.07
    ♈
    0.07
     sleek
    0.07
    Act Density 0.092%

    No Known Activations