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

    Neuronpedia

    INDEX
    Explanations

    Code repositories/GitHub URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dims
    -0.09
    innov
    -0.09
    vidence
    -0.08
    charges
    -0.08
    therapy
    -0.08
     gastron
    -0.08
    lx
    -0.08
     применение
    -0.08
    Innov
    -0.07
    da
    -0.07
    POSITIVE LOGITS
     cloning
    0.13
     Clone
    0.11
    .clone
    0.10
     SVN
    0.10
     git
    0.10
     svn
    0.10
     克
    0.10
    Clone
    0.09
    _clone
    0.09
     cloned
    0.09
    Act Density 0.007%

    No Known Activations