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

    Neuronpedia

    INDEX
    Explanations

    let's begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ellipsoid
    0.62
     inertia
    0.60
     densité
    0.56
     Bred
    0.56
     overfitting
    0.54
     CSS
    0.54
     disruption
    0.54
     Feynman
    0.52
    🚨
    0.51
     medico
    0.51
    POSITIVE LOGITS
    !:
    0.63
    !-
    0.63
    !’
    0.62
    !“
    0.62
     mulai
    0.61
    !»
    0.61
    !..
    0.61
     !,
    0.56
    :*
    0.55
    开始
    0.55
    Act Density 0.067%

    No Known Activations