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

    Neuronpedia

    INDEX
    Explanations

    whether something is or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \"
    0.60
    $("#
    0.58
    \">
    0.53
    ңыз
    0.50
     cumpl
    0.50
    \".
    0.49
     supposedly
    0.49
    ]));
    0.49
    \")
    0.48
     ponú
    0.48
    POSITIVE LOGITS
    ই
    0.63
     MediaQuery
    0.62
     intelligible
    0.61
    ਰ
    0.60
    ン
    0.60
     glycoprotein
    0.59
     reassured
    0.59
    라
    0.59
    ುದು
    0.58
    leet
    0.57
    Act Density 0.035%

    No Known Activations