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

    Neuronpedia

    INDEX
    Explanations

    tikz latex code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्किप
    0.38
     bathrooms
    0.38
    둰
    0.38
    MessageNow
    0.37
    厠
    0.36
     restrooms
    0.36
     జరిగిన
    0.35
    нена
    0.35
     स्व
    0.34
    0.34
    POSITIVE LOGITS
    1
    0.42
    7
    0.39
     ){
    0.38
    6
    0.38
    po
    0.38
    ic
    0.37
    9
    0.37
    vi
    0.37
    AMA
    0.36
    ){
    0.36
    Act Density 0.000%

    No Known Activations