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

    Neuronpedia

    INDEX
    Explanations

    in Entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कार्बन
    0.38
    농
    0.38
    Bru
    0.38
     canisters
    0.38
    Очень
    0.37
    দিনই
    0.37
    keit
    0.37
    Bitt
    0.36
     Bitt
    0.36
    Nou
    0.36
    POSITIVE LOGITS
     السما
    0.45
     Mosca
    0.41
     constit
    0.40
    lub
    0.40
    窕
    0.38
    backdrop
    0.37
    明らか
    0.37
     Include
    0.37
    譴
    0.36
     foo
    0.36
    Act Density 0.000%

    No Known Activations