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

    Neuronpedia

    INDEX
    Explanations

    identifier strings and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     STEELS
    0.50
    онів
    0.49
    PSC
    0.46
    ವಿಲ್ಲ
    0.46
     ALLOYS
    0.45
     गिलास
    0.44
     galactose
    0.44
    ಮಾಡ
    0.43
    뉜
    0.43
    managedbuild
    0.43
    POSITIVE LOGITS
    .
    0.55
    :
    0.48
    ;
    0.44
    Manager
    0.43
     Las
    0.43
    。
    0.43
     Manager
    0.41
    <?
    0.39
    "
    0.38
    ="
    0.38
    Act Density 0.001%

    No Known Activations