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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahy
    -0.07
    OU
    -0.07
     lit
    -0.06
    quences
    -0.06
    WA
    -0.06
    Taylor
    -0.06
    ์ต
    -0.06
     colony
    -0.06
     SR
    -0.06
     Macedonia
    -0.06
    POSITIVE LOGITS
     generously
    0.07
     gloss
    0.06
     Alma
    0.06
     Indo
    0.06
     economically
    0.06
     가능한
    0.06
     řed
    0.06
    	CG
    0.06
    _logic
    0.06
     ضو
    0.06
    Act Density 0.164%

    No Known Activations