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

    Neuronpedia

    INDEX
    Explanations

    vi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oste
    -0.08
    ounding
    -0.08
    虻
    -0.08
     net
    -0.07
     Nets
    -0.07
    WithName
    -0.07
     accountable
    -0.07
    ête
    -0.07
    nes
    -0.07
     fret
    -0.07
    POSITIVE LOGITS
     vi
    0.08
     olmuştur
    0.08
    したり
    0.07
    𝖞
    0.07
     origin
    0.07
    AdapterFactory
    0.07
     {}:
    0.07
    dü
    0.07
    👏
    0.06
    🗁
    0.06
    Act Density 0.012%

    No Known Activations