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

    Neuronpedia

    INDEX
    Explanations

    sales statistics, percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ic
    0.50
    orn
    0.49
    ረዳ
    0.48
     are
    0.47
     is
    0.46
    ombr
    0.46
     наша
    0.44
    ab
    0.44
     will
    0.43
     \
    0.43
    POSITIVE LOGITS
     Hearing
    0.46
     Multiply
    0.45
    遺
    0.44
     Telephone
    0.43
    WOR
    0.42
     Cul
    0.42
    𝑻
    0.42
     Coupled
    0.42
    湊
    0.41
    㳓
    0.41
    Act Density 0.000%

    No Known Activations