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

    Neuronpedia

    INDEX
    Explanations

    Contract logic: rules or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.04
    a
    1.03
    say
    1.02
    𝑌
    1.02
    ,$$
    0.99
    )!
    0.98
    ang
    0.94
    תוך
    0.92
     )।
    0.91
    Olymp
    0.91
    POSITIVE LOGITS
     britannique
    1.33
     offrent
    1.25
     présentant
    1.24
     régional
    1.17
     continueRoutine
    1.16
     persone
    1.16
     constitué
    1.15
     situés
    1.15
     Dorian
    1.13
     Rés
    1.12
    Act Density 0.000%

    No Known Activations