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

    Neuronpedia

    INDEX
    Explanations

    Neural network layer sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     사회
    -0.07
    -add
    -0.07
    _changed
    -0.07
    _BOOLEAN
    -0.07
    _less
    -0.07
    -case
    -0.07
    ział
    -0.06
    -CS
    -0.06
    missing
    -0.06
     destino
    -0.06
    POSITIVE LOGITS
     tactic
    0.07
    ildenafil
    0.06
     بازبینی
    0.06
    另外
    0.06
    англ
    0.06
    	glfw
    0.06
    	Size
    0.06
    .Quad
    0.06
    Jacob
    0.06
    ，就是
    0.06
    Act Density 0.004%

    No Known Activations