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

    Neuronpedia

    INDEX
    Explanations

    spot instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     добав
    0.45
     συνεργ
    0.45
    新增
    0.44
     शेयर
    0.44
     tmux
    0.44
     deportiva
    0.42
    И
    0.42
     обеспечи
    0.41
     initialise
    0.41
    二
    0.41
    POSITIVE LOGITS
    puted
    0.46
    arap
    0.44
    říve
    0.44
     counties
    0.43
     freely
    0.43
     questioned
    0.42
     gewisse
    0.42
    arom
    0.42
     mighty
    0.42
     Caldwell
    0.41
    Act Density 0.004%

    No Known Activations