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

    Neuronpedia

    INDEX
    Explanations

    few good men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     několik
    0.51
     kilku
    0.50
     několika
    0.46
    several
    0.41
     several
    0.41
     كيف
    0.40
     flera
    0.40
     어떻게
    0.40
    કેટ
    0.40
     niekoľ
    0.39
    POSITIVE LOGITS
     table
    0.50
     Table
    0.47
     clicks
    0.45
     Gaye
    0.44
     shots
    0.42
     minutes
    0.40
     Less
    0.40
     adım
    0.40
    Table
    0.39
    ership
    0.39
    Act Density 0.000%

    No Known Activations