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

    Neuronpedia

    INDEX
    Explanations

    with wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ylum
    -0.06
    ############
    -0.06
    byss
    -0.06
    Dos
    -0.06
    arness
    -0.06
    Ocean
    -0.06
    pecies
    -0.06
    _ib
    -0.06
    ingga
    -0.06
    quartered
    -0.06
    POSITIVE LOGITS
     philosophical
    0.07
     wom
    0.07
     Fuji
    0.07
     {?}
    0.06
     小
    0.06
    Arena
    0.06
     Böyle
    0.06
     Mo
    0.06
    ertainment
    0.06
     Cl
    0.06
    Act Density 0.017%

    No Known Activations