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

    Neuronpedia

    INDEX
    Explanations

    past ability/possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лений
    0.43
    Boulder
    0.42
    整数
    0.40
    形状
    0.39
    hasClass
    0.39
    COMMENT
    0.39
    ように
    0.39
    LIGHT
    0.38
     ಮಾತನಾಡ
    0.38
    пись
    0.38
    POSITIVE LOGITS
     Poland
    0.50
     names
    0.50
     escrow
    0.49
     pathologies
    0.47
     Eastern
    0.47
     countries
    0.46
     eastern
    0.45
     passive
    0.45
     pathology
    0.45
     Polish
    0.45
    Act Density 0.000%

    No Known Activations