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

    Neuronpedia

    INDEX
    Explanations

    focusing on effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Workshop
    0.52
    ീപ
    0.50
     Setup
    0.46
    OMe
    0.46
     Lhasa
    0.46
     MSI
    0.46
    Workshop
    0.45
     Particle
    0.45
     Coke
    0.45
     McDowell
    0.45
    POSITIVE LOGITS
    거
    0.46
    hent
    0.45
    र्ग
    0.44
     illustrious
    0.42
     elegantes
    0.42
     solucion
    0.41
     globalisation
    0.40
     complacent
    0.40
    ய்
    0.39
    legen
    0.39
    Act Density 0.039%

    No Known Activations