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

    Neuronpedia

    INDEX
    Explanations

    code attributes and nodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centerY
    0.26
    जानकारी
    0.24
     һәм
    0.21
    Saludos
    0.20
    𝙣
    0.20
    梩
    0.20
     combinación
    0.20
    。</
    0.20
    Источник
    0.20
    ம்பர்
    0.20
    POSITIVE LOGITS
     has
    0.25
     trivially
    0.24
     monetize
    0.24
     cheap
    0.24
     dilemma
    0.24
     لا
    0.24
     is
    0.23
     non
    0.23
     uber
    0.23
     hack
    0.23
    Act Density 0.095%

    No Known Activations