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

    Neuronpedia

    INDEX
    Explanations

    row/rows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pikachu
    -0.07
     Βασ
    -0.07
    CLEAR
    -0.07
    ايت
    -0.07
    edio
    -0.07
    чер
    -0.07
     Verg
    -0.07
     TPP
    -0.07
     wissen
    -0.06
    iph
    -0.06
    POSITIVE LOGITS
    utut
    0.07
     наб
    0.06
    undry
    0.06
    razil
    0.06
     Haw
    0.06
    .roll
    0.06
    returnValue
    0.06
     rx
    0.06
    .follow
    0.06
     cramped
    0.06
    Act Density 0.004%

    No Known Activations