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

    Neuronpedia

    INDEX
    Explanations

    foreign and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Компания
    0.40
     flood
    0.37
     дополни
    0.36
     ダイ
    0.35
    wound
    0.34
    ษัท
    0.34
     घना
    0.34
    განი
    0.34
     после
    0.34
     அட
    0.34
    POSITIVE LOGITS
     Resources
    0.43
     suivi
    0.40
    atch
    0.40
     acol
    0.38
     weinig
    0.38
     poche
    0.37
     Res
    0.36
     आश्रम
    0.36
    achtige
    0.35
     اظهار
    0.35
    Act Density 0.000%

    No Known Activations