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

    Neuronpedia

    INDEX
    Explanations

    escaping or trapped

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *)"
    -0.07
    	K
    -0.07
    اشین
    -0.07
    ()"↵
    -0.06
     UNIVERS
    -0.06
    _profiles
    -0.06
     becomes
    -0.06
    _mgmt
    -0.06
    q
    -0.06
    imes
    -0.06
    POSITIVE LOGITS
     alertDialog
    0.08
    рет
    0.07
    .putInt
    0.07
    ToolBar
    0.07
     appended
    0.06
     Kiev
    0.06
    .disconnect
    0.06
     Boone
    0.06
    رة
    0.06
     Armen
    0.06
    Act Density 0.012%

    No Known Activations