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

    Neuronpedia

    INDEX
    Explanations

    followed by sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lices
    0.32
    もので
    0.31
     dumpling
    0.29
     tog
    0.28
    arela
    0.28
     iy
    0.27
     decon
    0.27
    ason
    0.27
     후
    0.26
     practical
    0.26
    POSITIVE LOGITS
    archiviato
    0.44
     Continued
    0.36
    透露
    0.35
    Continued
    0.35
     ವಿದ
    0.34
     आतंकवादी
    0.33
     FISA
    0.32
    continued
    0.32
     siglas
    0.32
     teilweise
    0.31
    Act Density 0.000%

    No Known Activations