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

    Neuronpedia

    INDEX
    Explanations

    context to topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🦊
    0.50
    孅
    0.45
    ել
    0.45
     traducción
    0.44
     Wilcox
    0.42
     mixing
    0.42
     mixers
    0.42
     বণ্টন
    0.41
    মুখী
    0.41
    伸ば
    0.41
    POSITIVE LOGITS
    ત
    0.38
    ordinary
    0.38
    arh
    0.38
    ho
    0.38
    Invit
    0.38
    ps
    0.38
    alamat
    0.38
    ups
    0.37
    g
    0.37
    ul
    0.37
    Act Density 0.005%

    No Known Activations