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

    Neuronpedia

    INDEX
    Explanations

    common cause of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actuators
    1.31
     xyz
    1.29
     benzoate
    1.24
    xyl
    1.19
     Bezos
    1.19
     activations
    1.18
     xyl
    1.17
     volunt
    1.17
     Yam
    1.15
     Woodruff
    1.15
    POSITIVE LOGITS
     Ireland
    1.83
     Irish
    1.74
    Irish
    1.68
    Ireland
    1.66
     irland
    1.61
     Dublin
    1.58
    Dublin
    1.56
     Irishman
    1.49
     Irland
    1.43
     ireland
    1.38
    Act Density 0.597%

    No Known Activations