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

    Neuronpedia

    INDEX
    Explanations

    language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৩৯
    0.48
    AK
    0.44
    3
    0.42
    ስቃ
    0.42
     戦
    0.41
     функцию
    0.41
     तुमचे
    0.40
     父
    0.40
     ষে
    0.40
    ǎi
    0.40
    POSITIVE LOGITS
    ;
    0.58
    x
    0.56
    ר
    0.56
    n
    0.55
    ,
    0.55
     for
    0.52
    ↵
    0.51
     attendants
    0.47
    ad
    0.46
     iemand
    0.45
    Act Density 0.104%

    No Known Activations