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

    Neuronpedia

    INDEX
    Explanations

    section starters after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftan
    0.44
     multifaceted
    0.37
    Hfn
    0.37
    TakeVideo
    0.36
     verwendeten
    0.35
     deton
    0.34
     stylistic
    0.34
     fenómeno
    0.34
    TextViewStyle
    0.32
     verbinden
    0.32
    POSITIVE LOGITS
     همچنین
    0.43
     ALSO
    0.42
     PLUS
    0.41
     THEN
    0.39
     WHICH
    0.38
     But
    0.38
     এছাড়াও
    0.38
     AND
    0.38
     It
    0.38
     Because
    0.37
    Act Density 0.363%

    No Known Activations