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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrêter
    -0.61
     us
    -0.52
    ($__
    -0.47
    álat
    -0.46
     to
    -0.45
    onies
    -0.45
     estrema
    -0.45
     ampio
    -0.45
    abbé
    -0.45
    reciated
    -0.45
    POSITIVE LOGITS
    GEBURTS
    0.60
    ethical
    0.58
    "]="
    0.55
    educational
    0.52
    assis
    0.52
    rights
    0.52
    historical
    0.50
    /
    0.50
    ]';
    0.50
    cultural
    0.50
    Act Density 0.050%

    No Known Activations