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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .³
    0.77
     sobretudo
    0.74
    fourths
    0.74
    Vega
    0.73
    Four
    0.73
    ④
    0.70
    ₃
    0.70
    음을
    0.69
     خمسه
    0.69
    FOUR
    0.69
    POSITIVE LOGITS
     optimizing
    0.91
     Steps
    0.90
     important
    0.90
     steps
    0.89
     Sample
    0.85
     Important
    0.83
     limiting
    0.82
     avoiding
    0.81
     Considerations
    0.81
     sample
    0.80
    Act Density 0.142%

    No Known Activations