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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Meanwhile
    -0.06
    Todo
    -0.06
     mag
    -0.06
     simpler
    -0.06
     Lost
    -0.06
     cot
    -0.05
     cuốn
    -0.05
     رز
    -0.05
     Wolf
    -0.05
     explanations
    -0.05
    POSITIVE LOGITS
    _inches
    0.09
    _MOUSE
    0.08
    _HOUR
    0.07
    _docs
    0.07
    970
    0.07
    toThrow
    0.07
    _ini
    0.07
    (fileName
    0.07
     }}}
    0.06
    ([
↵
    0.06
    Act Density 0.007%

    No Known Activations