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

    Neuronpedia

    INDEX
    Explanations

    compatibility settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yne
    2.58
    दार
    2.53
    𝙜
    2.49
    țele
    2.40
    দানি
    2.39
    $('#
    2.37
     spindles
    2.34
     hoops
    2.33
    $("#
    2.33
    ів
    2.28
    POSITIVE LOGITS
    ০
    3.39
    क
    3.13
    z
    2.83
     Recordemos
    2.78
    te
    2.69
     Одна
    2.64
     arct
    2.54
    在意
    2.46
    м
    2.44
    к
    2.44
    Act Density 0.001%

    No Known Activations