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

    Neuronpedia

    INDEX
    Explanations

    Hollywood and Los Angeles locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    диви
    0.63
    д
    0.61
    та
    0.58
    zioni
    0.55
    യി
    0.54
    டன்
    0.53
    cción
    0.53
    isr
    0.52
     soal
    0.51
     demikian
    0.51
    POSITIVE LOGITS
    мония
    0.58
    OT
    0.50
    son
    0.50
    ことが
    0.49
    Accueil
    0.49
    petite
    0.48
    omości
    0.47
     putea
    0.47
    premi
    0.46
    in
    0.46
    Act Density 0.006%

    No Known Activations