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

    Neuronpedia

    INDEX
    Explanations

    scalable architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ip
    0.52
    ball
    0.51
    steak
    0.51
    oll
    0.50
    École
    0.48
    سات
    0.47
    op
    0.46
    hol
    0.46
    trace
    0.46
    adou
    0.46
    POSITIVE LOGITS
     filtra
    0.49
     guida
    0.49
     tempered
    0.47
     nasa
    0.46
     രാവിലെ
    0.45
     lista
    0.45
     deaktiv
    0.45
     retrait
    0.44
     Udemy
    0.44
     didik
    0.44
    Act Density 0.000%

    No Known Activations