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

    Neuronpedia

    INDEX
    Explanations

    debate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EClass
    -0.51
    uzzy
    -0.50
    endipity
    -0.49
    ://$
    -0.48
     indefinite
    -0.48
    tralight
    -0.48
    Ư
    -0.47
     EdgeInsets
    -0.45
    ;"></
    -0.45
    qrstuvwxyz
    -0.45
    POSITIVE LOGITS
     teams
    0.57
    jalá
    0.56
    endphp
    0.56
    0.56
     committees
    0.56
    IntoConstraints
    0.56
     betweenstory
    0.55
     internos
    0.55
     Competition
    0.54
     team
    0.53
    Act Density 0.002%

    No Known Activations