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

    Neuronpedia

    INDEX
    Explanations

    then introduces something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dragged
    0.45
    amburger
    0.43
    zc
    0.42
     শেষের
    0.42
     callable
    0.41
     تضيفلها
    0.41
    DAAR
    0.41
    ChooserView
    0.41
     TComponent
    0.40
     signalling
    0.40
    POSITIVE LOGITS
     $
    0.42
     DIC
    0.42
    सरा
    0.40
     cotton
    0.40
     metamorph
    0.40
     mils
    0.40
     firef
    0.39
    newswire
    0.39
     coton
    0.39
     derrota
    0.39
    Act Density 0.007%

    No Known Activations