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

    Neuronpedia

    INDEX
    Explanations

    Greetings and appreciation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.74
    wpi
    -0.69
     Numerade
    -0.55
     préférable
    -0.54
    gimento
    -0.54
    retudo
    -0.53
     linkovi
    -0.52
    hidup
    -0.52
     муніципалі
    -0.51
    PositiveButton
    -0.50
    POSITIVE LOGITS
     message
    0.85
     gift
    0.77
     letter
    0.76
     note
    0.71
     dinner
    0.70
     concert
    0.67
     email
    0.65
     plaque
    0.64
     page
    0.63
     post
    0.62
    Act Density 0.001%

    No Known Activations