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

    Neuronpedia

    INDEX
    Explanations

    comparisons using like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     其中
    0.75
    otides
    0.69
    ibaldi
    0.68
     welchen
    0.66
     यांचा
    0.65
     welchem
    0.65
     இவற்றை
    0.64
     यांच्या
    0.63
    ませ
    0.63
     وذلك
    0.62
    POSITIVE LOGITS
     like
    6.96
     Like
    6.20
    Like
    6.06
    like
    5.69
     LIKE
    5.35
     seperti
    5.08
     như
    4.94
    LIKE
    4.54
     مثل
    4.47
     مانند
    4.47
    Act Density 1.832%

    No Known Activations