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

    Neuronpedia

    INDEX
    Explanations

    href

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rows
    -0.07
    _x
    -0.07
    Empresa
    -0.07
    iversity
    -0.06
    Distribution
    -0.06
    	Log
    -0.06
    	log
    -0.06
    -line
    -0.06
     $$$
    -0.06
    킬
    -0.06
    POSITIVE LOGITS
    Href
    0.09
    _href
    0.08
    اهر
    0.07
     href
    0.07
     gruesome
    0.07
     glfw
    0.07
    .visitInsn
    0.06
    href
    0.06
     daemon
    0.06
    _sell
    0.06
    Act Density 0.005%

    No Known Activations