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

    Neuronpedia

    INDEX
    Explanations

    a cellphone/smartphone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WHAT
    0.18
     i
    0.18
     What
    0.17
     vs
    0.16
    ((
    0.16
    ;
    0.16
     isto
    0.16
     Erfahrungen
    0.16
    ----
    0.15
     Versus
    0.15
    POSITIVE LOGITS
    टील
    0.17
    اهر
    0.17
    აციის
    0.17
    शिलाजीत
    0.16
    ন্থা
    0.16
    aadhar
    0.16
    ।]
    0.16
    ებულია
    0.16
    ಚಿತ
    0.15
     synthesized
    0.15
    Act Density 0.042%

    No Known Activations