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

    Neuronpedia

    INDEX
    Explanations

    programming commands and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Servlet
    0.44
    :</
    0.43
    :");
    0.41
    :";
    0.41
    HttpPut
    0.39
    以下の
    0.39
    :[/
    0.38
    7
    0.38
     thisTrial
    0.37
    以下的
    0.37
    POSITIVE LOGITS
     değiş
    0.42
     بعد
    0.42
    !),
    0.41
     btw
    0.39
     meski
    0.39
     ві
    0.38
     dla
    0.37
    ↵↵
    0.37
     עם
    0.37
     från
    0.36
    Act Density 0.236%

    No Known Activations