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

    Neuronpedia

    INDEX
    Explanations

    работ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hop
    -0.07
    آخر
    -0.07
    在现场
    -0.07
     Sanctuary
    -0.07
    ườ
    -0.07
    炽
    -0.06
    環境
    -0.06
    מכשיר
    -0.06
     Milan
    -0.06
    linik
    -0.06
    POSITIVE LOGITS
     forging
    0.07
     CString
    0.07
    	ct
    0.07
     Creation
    0.07
    ":{"
    0.07
    וצאות
    0.07
     bureaucratic
    0.07
    _consts
    0.06
     Obamacare
    0.06
    arcer
    0.06
    Act Density 0.003%

    No Known Activations