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

    Neuronpedia

    INDEX
    Explanations

    URLs and placeholders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ypy
    -0.07
    XPath
    -0.06
     transporter
    -0.06
    _accuracy
    -0.06
    �
    -0.06
    Memory
    -0.06
    healthy
    -0.06
     Lawyers
    -0.06
     прог
    -0.06
    .guild
    -0.06
    POSITIVE LOGITS
     perme
    0.07
    	RTCT
    0.07
    務
    0.06
     etti
    0.06
     Palmer
    0.06
     rak
    0.06
    (Exception
    0.06
     ран
    0.06
     #↵
    0.06
     bere
    0.06
    Act Density 0.004%

    No Known Activations