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

    Neuronpedia

    INDEX
    Explanations

    Without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الحياه
    -0.60
    '][]
    -0.59
    出版年
    -0.55
    ModelSerializer
    -0.55
     gedaan
    -0.54
     betweenstory
    -0.53
    acakt
    -0.49
     која
    -0.48
    basics
    -0.48
    눠
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.74
    Referències
    0.65
    ništvo
    0.64
     proper
    0.64
     Benefit
    0.62
     doubt
    0.61
     Gain
    0.59
     Access
    0.57
    URLException
    0.57
    aarrggbb
    0.55
    Act Density 0.004%

    No Known Activations