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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     secretly
    -0.07
    <>();↵↵
    -0.07
    _client
    -0.07
    SIG
    -0.07
     eat
    -0.07
    ilim
    -0.06
     described
    -0.06
     visible
    -0.06
     sensitive
    -0.06
     "~
    -0.06
    POSITIVE LOGITS
     overclock
    0.07
    HOW
    0.06
     fellow
    0.06
     what
    0.06
    (AdapterView
    0.06
     moder
    0.06
     Pinterest
    0.06
     bakeka
    0.06
    PasswordEncoder
    0.06
    .Database
    0.06
    Act Density 0.011%

    No Known Activations