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

    Neuronpedia

    INDEX
    Explanations

    Dominic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cru
    -0.07
     greeted
    -0.06
     Eva
    -0.06
     LOOP
    -0.06
     luxury
    -0.06
    alette
    -0.06
     ENC
    -0.06
     naturally
    -0.06
    gcd
    -0.06
     inventory
    -0.06
    POSITIVE LOGITS
     €
    0.07
     نسمة
    0.07
     найти
    0.07
    .sendMessage
    0.07
     Millennials
    0.06
     Doming
    0.06
    much
    0.06
     svenska
    0.06
     Deg
    0.06
    醴
    0.06
    Act Density 0.003%

    No Known Activations