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

    Neuronpedia

    INDEX
    Explanations

    liquid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whereabouts
    -0.08
    sign
    -0.07
     owe
    -0.07
    AND
    -0.07
     mơ
    -0.07
     hay
    -0.06
    넣
    -0.06
    _serialize
    -0.06
    大多数人
    -0.06
    雅
    -0.06
    POSITIVE LOGITS
    `}
    0.07
     orden
    0.07
     markdown
    0.07
    破坏
    0.07
     ileti
    0.07
    .gridColumn
    0.07
    𝚄
    0.06
     elek
    0.06
     Fond
    0.06
     mes
    0.06
    Act Density 0.007%

    No Known Activations