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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旦
    -0.08
    signals
    -0.07
    Bubble
    -0.06
    看
    -0.06
    осуд
    -0.06
    _MODIFIED
    -0.06
    .dup
    -0.06
    _lhs
    -0.06
    _basename
    -0.06
    getSingleton
    -0.06
    POSITIVE LOGITS
     scholarships
    0.07
    >;↵↵
    0.06
     春
    0.06
     emacs
    0.06
     arbitrary
    0.06
     Five
    0.06
     Hungary
    0.06
    Thirty
    0.06
     Australian
    0.06
     author
    0.06
    Act Density 0.018%

    No Known Activations