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

    Neuronpedia

    INDEX
    Explanations

    GE, Q, T, Today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     composting
    -0.81
     Pilate
    -0.81
     olma
    -0.74
     Scripts
    -0.74
     scoping
    -0.73
     appraise
    -0.73
     collusion
    -0.73
     anhydrous
    -0.73
    پایی
    -0.72
     Crete
    -0.71
    POSITIVE LOGITS
     GE
    1.53
    GE
    1.21
     Schenectady
    1.14
    ectady
    0.88
    medical
    0.82
    industrial
    0.78
     materiale
    0.77
    骠
    0.75
     industrial
    0.75
    .$.
    0.74
    Act Density 0.011%

    No Known Activations