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

    Neuronpedia

    INDEX
    Explanations

    IR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scot
    -0.06
    Inter
    -0.06
     Grocery
    -0.06
     mo
    -0.06
     overl
    -0.06
     bại
    -0.06
    ступ
    -0.06
     Rust
    -0.06
     justice
    -0.06
    -home
    -0.06
    POSITIVE LOGITS
    えた
    0.08
    /save
    0.07
     programa
    0.07
    ποιη
    0.07
    =create
    0.07
     sieht
    0.07
    acoes
    0.07
    $username
    0.07
    ्सर
    0.07
     یا
    0.07
    Act Density 0.003%

    No Known Activations