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

    Neuronpedia

    INDEX
    Explanations

    be no, better pace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.52
    z
    0.49
    Buenas
    0.48
    voll
    0.47
    TERN
    0.46
     !
    0.45
     repet
    0.45
    )!
    0.45
     glare
    0.45
    ешь
    0.44
    POSITIVE LOGITS
    ૫
    0.50
    工程师
    0.48
     Uw
    0.46
     Prescott
    0.46
     Schuyler
    0.46
    पक
    0.45
     ይህም
    0.45
    āla
    0.45
     Committee
    0.44
     Lyman
    0.44
    Act Density 0.000%

    No Known Activations