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

    Neuronpedia

    INDEX
    Explanations

    Alphanumeric sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     année
    -0.07
     Asians
    -0.07
     mostr
    -0.06
     cyk
    -0.06
    /D
    -0.06
     mediante
    -0.06
     Vander
    -0.06
    >D
    -0.06
     cz
    -0.06
    acji
    -0.06
    POSITIVE LOGITS
    學
    0.07
     valued
    0.07
    ichern
    0.07
    Saving
    0.07
     unre
    0.06
    -т
    0.06
     Nin
    0.06
    ]?
    0.06
    extr
    0.06
     erhalten
    0.06
    Act Density 0.004%

    No Known Activations