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

    Neuronpedia

    INDEX
    Explanations

    and do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ktops
    0.34
    tero
    0.33
    oxide
    0.33
    Times
    0.33
    December
    0.33
    দাস
    0.33
    atitis
    0.32
     monoxide
    0.32
    resham
    0.32
    地の
    0.31
    POSITIVE LOGITS
     iy
    0.43
    ပါ
    0.38
    spruch
    0.38
    <unused2135>
    0.38
     cuy
    0.37
     iya
    0.37
    lyPlugin
    0.37
     cordova
    0.37
    캇
    0.36
     iaa
    0.36
    Act Density 0.001%

    No Known Activations