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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’air
    -0.09
     nz
    -0.08
    -0.08
     ĝin
    -0.08
    Tem
    -0.08
    'air
    -0.08
    Nd
    -0.07
     mis
    -0.07
    инку
    -0.07
    Mist
    -0.07
    POSITIVE LOGITS
    tout
    0.08
    拳
    0.08
     ferrovi
    0.08
    .Constraint
    0.08
    ================================================================================
    0.08
     규
    0.07
     desempeño
    0.07
     escrib
    0.07
    _req
    0.07
    ್ಮಿಕ
    0.07
    Act Density 0.006%
    No Known Activations