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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nex
    -0.07
    .trade
    -0.07
     Nom
    -0.07
    iphery
    -0.06
     sorted
    -0.06
     Savaşı
    -0.06
    шись
    -0.06
     Batt
    -0.06
     DD
    -0.06
    368
    -0.06
    POSITIVE LOGITS
    наче
    0.07
    .ping
    0.06
    	ext
    0.06
     Technician
    0.06
    ・━
    0.06
    iasm
    0.06
    vik
    0.06
     робіт
    0.06
    inflate
    0.06
     Buddhism
    0.06
    Act Density 0.001%

    No Known Activations