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

    Neuronpedia

    INDEX
    Explanations

    computer networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    brane
    -0.08
    低温
    -0.07
     NAN
    -0.07
    monary
    -0.07
     Cou
    -0.07
     Tournament
    -0.06
     vicious
    -0.06
    III
    -0.06
    不同的
    -0.06
    Permissions
    -0.06
    POSITIVE LOGITS
    	eval
    0.07
    დ
    0.07
    _pass
    0.07
    _xs
    0.07
    素养
    0.07
    _press
    0.07
    ...↵↵↵↵↵↵
    0.07
    след
    0.07
    "?>↵
    0.07
    (scanner
    0.07
    Act Density 0.100%

    No Known Activations