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

    Neuronpedia

    INDEX
    Explanations

    code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    painter
    0.40
    WebV
    0.39
    ernes
    0.39
     पोजीशन
    0.39
    ジャパン
    0.38
     fascin
    0.38
    Ligações
    0.38
     সিনেম
    0.37
     จํา
    0.37
     négoci
    0.36
    POSITIVE LOGITS
    setOutput
    0.39
    unset
    0.38
    বাম
    0.38
    Rahul
    0.36
     OUTPUT
    0.35
     izin
    0.35
    ıç
    0.35
    Output
    0.34
    Assistant
    0.34
     DAW
    0.34
    Act Density 0.006%

    No Known Activations