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

    Neuronpedia

    INDEX
    Explanations

    Nonsense text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     was
    -0.09
     were
    -0.08
     became
    -0.07
     Execution
    -0.07
     write
    -0.07
    可以
    -0.06
     been
    -0.06
    _vc
    -0.06
    Markup
    -0.06
     sworn
    -0.06
    POSITIVE LOGITS
    privileged
    0.06
     MEM
    0.06
    _MINOR
    0.06
    _KeyPress
    0.06
    .userid
    0.06
     listopadu
    0.06
    .Light
    0.06
    HEST
    0.06
     IND
    0.06
    localhost
    0.06
    Act Density 0.300%

    No Known Activations