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

    Neuronpedia

    INDEX
    Explanations

    programming commands and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    excluding
    0.64
    are
    0.60
    IA
    0.59
    াজি
    0.58
    ان
    0.57
    With
    0.55
    awara
    0.55
     ومع
    0.54
    CLUDES
    0.53
     থাকছে
    0.53
    POSITIVE LOGITS
     to
    0.66
    </h3>
    0.66
     bitcoins
    0.61
     pequena
    0.59
     pequeno
    0.59
     antigos
    0.59
     zinc
    0.58
     pequenos
    0.58
     Новый
    0.58
     ш
    0.58
    Act Density 0.145%

    No Known Activations