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

    Neuronpedia

    INDEX
    Explanations

    Descriptive language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decoding
    -0.07
    -tank
    -0.07
    拉
    -0.07
    inou
    -0.07
    Deploy
    -0.07
    041
    -0.06
     erfahren
    -0.06
    ambique
    -0.06
     radar
    -0.06
    Syn
    -0.06
    POSITIVE LOGITS
     Bylo
    0.07
    ragment
    0.06
    bote
    0.06
    ).'
    0.06
     ayır
    0.06
     очист
    0.06
    istingu
    0.06
    )c
    0.06
    θεν
    0.06
     scav
    0.06
    Act Density 0.071%

    No Known Activations