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

    Neuronpedia

    INDEX
    Explanations

    Utils, helpers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     originated
    -0.07
     lateral
    -0.06
     mũi
    -0.06
    _keyboard
    -0.06
    phants
    -0.06
     déc
    -0.06
     highways
    -0.06
     famine
    -0.06
    Iran
    -0.06
     причин
    -0.06
    POSITIVE LOGITS
    Vals
    0.07
    Compare
    0.07
    ,line
    0.06
     gặp
    0.06
    ';";↵
    0.06
     infused
    0.06
    ]};↵
    0.06
    );*/↵
    0.06
    Mask
    0.06
    _DONE
    0.06
    Act Density 0.022%

    No Known Activations