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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    belt
    -0.07
    Pixels
    -0.07
     Sisters
    -0.07
    _dual
    -0.07
    běh
    -0.06
    distributed
    -0.06
    _corner
    -0.06
    り
    -0.06
    safe
    -0.06
    Hour
    -0.06
    POSITIVE LOGITS
    ufreq
    0.08
    ISHED
    0.06
     disastrous
    0.06
    ωμά
    0.06
     respected
    0.06
    -->
↵
    0.06
     jugg
    0.06
     अग
    0.06
    WA
    0.06
    CppMethodPointer
    0.06
    Act Density 0.003%

    No Known Activations