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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _patches
    -0.07
     хви
    -0.07
    Round
    -0.06
     unethical
    -0.06
    λλην
    -0.06
     LAP
    -0.06
    gaben
    -0.06
    before
    -0.06
    ilen
    -0.06
    Looper
    -0.06
    POSITIVE LOGITS
     změn
    0.06
    آم
    0.06
     tablename
    0.06
    (Log
    0.06
     techno
    0.06
    　　　　 　 　
    0.06
    	cmd
    0.06
     Voor
    0.06
     nedir
    0.06
    �
    0.05
    Act Density 0.026%

    No Known Activations