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

    Neuronpedia

    INDEX
    Explanations

    sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ал
    -0.07
     parliamentary
    -0.07
     Bast
    -0.07
    longitude
    -0.07
    ко
    -0.06
     audience
    -0.06
     permitted
    -0.06
     jobs
    -0.06
    а
    -0.06
     franchise
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵↵↵↵
    0.06
     vữ
    0.06
    (paren
    0.06
    routeParams
    0.06
     moderne
    0.06
    /projects
    0.06
    	retval
    0.06
    osl
    0.06
     yerine
    0.06
     иму
    0.06
    Act Density 0.013%

    No Known Activations