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

    Neuronpedia

    INDEX
    Explanations

    2 following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এদিন
    0.91
     ninth
    0.89
     VIII
    0.88
    [.
    0.83
    ⑧
    0.82
    ércoles
    0.81
     époque
    0.81
    ><%=
    0.81
     Match
    0.80
     시간에
    0.80
    POSITIVE LOGITS
    2
    0.62
     LOD
    0.62
     igen
    0.56
    nextNode
    0.56
     pagos
    0.55
    ஸ்க
    0.53
    ux
    0.51
    Custom
    0.51
    க்ஸ
    0.51
    详解
    0.50
    Act Density 0.139%

    No Known Activations