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

    Neuronpedia

    INDEX
    Explanations

    Vicuna-13B fine-tuning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிறது
    0.44
    的最
    0.41
     Synchronization
    0.40
    Dimension
    0.39
    цията
    0.39
    Synchronization
    0.38
     Optimization
    0.38
    PARAMETERS
    0.38
     தொ
    0.38
     Practical
    0.38
    POSITIVE LOGITS
     rav
    0.47
    Raven
    0.46
     Ravens
    0.45
     Raven
    0.44
    rav
    0.41
    Flame
    0.41
    Rav
    0.40
    ޫ
    0.40
     Fl
    0.39
     aggregate
    0.39
    Act Density 0.014%

    No Known Activations