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

    Neuronpedia

    INDEX
    Explanations

    height assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    0.38
    Industrial
    0.37
    Ru
    0.36
    ্য
    0.35
    lukan
    0.35
    acter
    0.34
    hj
    0.34
    ม
    0.34
    ற்ற
    0.34
     упо
    0.33
    POSITIVE LOGITS
     opsi
    0.47
     ident
    0.47
    ന്തപു
    0.46
     inégal
    0.45
     identifik
    0.43
     identify
    0.43
     proportionately
    0.42
     anomal
    0.42
     opleiding
    0.42
     तुझ्या
    0.42
    Act Density 0.001%

    No Known Activations