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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urally
    -0.07
     numer
    -0.07
     scattering
    -0.07
    änge
    -0.06
     вели
    -0.06
     получения
    -0.06
     Pavel
    -0.06
     cultura
    -0.06
    -Ta
    -0.06
    -parse
    -0.06
    POSITIVE LOGITS
     thirsty
    0.07
    OTO
    0.07
    TMP
    0.06
    menuItem
    0.06
     heb
    0.06
    izzazione
    0.06
    �от
    0.06
    =logging
    0.06
     consolidate
    0.06
    install
    0.06
    Act Density 0.019%

    No Known Activations