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

    Neuronpedia

    INDEX
    Explanations

    Mixed languages and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "]),
    -0.60
     ")";
    -0.57
    \"");
    -0.56
    IVEREF
    -0.55
     Man
    -0.54
     Temple
    -0.54
     S
    -0.53
     Che
    -0.52
    ctis
    -0.52
    ''')
    -0.52
    POSITIVE LOGITS
     @__
    0.54
    Personensuche
    0.52
    tone
    0.52
     NACIONAL
    0.52
     aapt
    0.51
     Administrativna
    0.49
     annuelle
    0.49
     elétrico
    0.48
    tones
    0.48
     fratelli
    0.47
    Act Density 0.122%

    No Known Activations