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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _buf
    -0.06
     [{'
    -0.06
    wish
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
    pathname
    -0.06
     lifespan
    -0.06
    	push
    -0.05
    departureday
    -0.05
          
↵
    -0.05
    .AddWithValue
    -0.05
    POSITIVE LOGITS
    eci
    0.07
     Portable
    0.07
    amed
    0.07
    _skill
    0.06
    Portable
    0.06
    edeki
    0.06
    ?)
    0.06
    -Identifier
    0.06
    -Americans
    0.06
    nému
    0.06
    Act Density 0.047%

    No Known Activations