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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -country
    -0.08
     COUNTRY
    -0.07
    онах
    -0.07
     conseguimos
    -0.07
     boats
    -0.07
     toutefois
    -0.07
    олага
    -0.07
    idding
    -0.07
    ોલ
    -0.07
    OLF
    -0.07
    POSITIVE LOGITS
     berikut
    0.09
    ser
    0.08
     faria
    0.08
    ientos
    0.08
     gating
    0.07
     handshake
    0.07
    _encoding
    0.07
     inherent
    0.07
     illusions
    0.07
     explained
    0.07
    Act Density 0.031%

    No Known Activations