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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sporad
    0.44
    դ
    0.42
     त्यात
    0.42
     dle
    0.40
    }|^{
    0.40
    damn
    0.40
     sporadically
    0.39
    ात
    0.39
    ਜ
    0.39
    ç
    0.38
    POSITIVE LOGITS
     <!--
    0.51
     //
    0.49
     或者
    0.46
     અથવા
    0.46
    <!--
    0.45
     অথবা
    0.45
     ////
    0.45
     또는
    0.45
    ;//
    0.45
     ataupun
    0.44
    Act Density 0.163%

    No Known Activations