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

    Neuronpedia

    INDEX
    Explanations

    technical documentation and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Empress
    0.45
     \%,
    0.40
     Queens
    0.40
     nasa
    0.38
     météor
    0.38
     Emp
    0.38
     dala
    0.37
     pas
    0.36
     Sahara
    0.36
     Nasa
    0.36
    POSITIVE LOGITS
    mml
    0.38
    ட்சிய
    0.38
    XML
    0.38
     kosten
    0.37
    Feeding
    0.37
    コスト
    0.37
    <unused16>
    0.36
    orkan
    0.36
    authier
    0.36
     criando
    0.36
    Act Density 0.000%

    No Known Activations