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

    Neuronpedia

    INDEX
    Explanations

    continued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isory
    -0.06
    ічного
    -0.06
    аніт
    -0.06
    atedRoute
    -0.06
     seks
    -0.06
    _gen
    -0.06
    _ax
    -0.06
    _figure
    -0.06
     Nexus
    -0.06
     persecuted
    -0.06
    POSITIVE LOGITS
     continued
    0.09
     graceful
    0.08
    .';↵
    0.07
     Said
    0.07
     Continued
    0.07
    ')),
    0.07
     "))
    0.07
     ""));↵
    0.07
    \")
    0.07
     plug
    0.06
    Act Density 0.006%

    No Known Activations