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

    Neuronpedia

    INDEX
    Explanations

    Directories and roots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Design
    -0.07
    icens
    -0.07
     Cs
    -0.06
     Av
    -0.06
    (pass
    -0.06
     fuck
    -0.06
    stdin
    -0.06
     dagen
    -0.06
     comforting
    -0.06
     decorated
    -0.06
    POSITIVE LOGITS
    -->
↵
    0.06
     خدمت
    0.06
    ('/');↵
    0.06
    .slf
    0.06
    .Servlet
    0.06
     відвід
    0.06
     Metodo
    0.06
    (direction
    0.06
    ’↵↵
    0.05
    سه
    0.05
    Act Density 0.018%

    No Known Activations