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

    Neuronpedia

    INDEX
    Explanations

    pauses and new clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    -1.53
    ?
    -1.28
    ggars
    -1.23
    ](
    -1.22
       
    -1.21
    ();
    -1.16
    &#
    -1.16
               
    -1.13
    __':
    -1.13
    >();
    -1.12
    POSITIVE LOGITS
     mutfak
    1.38
     таких
    1.30
     these
    1.30
    🏬
    1.27
     parfüm
    1.27
     but
    1.20
     portugués
    1.17
    푀
    1.16
    🫤
    1.16
     solche
    1.16
    Act Density 0.142%

    No Known Activations