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

    Neuronpedia

    INDEX
    Explanations

    web pages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пое
    0.53
    肃
    0.53
     sparrow
    0.53
    DataAnnotations
    0.51
     bean
    0.51
    Bom
    0.51
     pli
    0.50
     halos
    0.50
    Quarter
    0.50
     anomal
    0.49
    POSITIVE LOGITS
     informado
    0.68
     informatique
    0.68
    ூட
    0.66
     محیط
    0.66
     locaux
    0.65
     createContext
    0.64
    週末
    0.64
     Eingang
    0.63
    嵌入
    0.63
     માહિતી
    0.63
    Act Density 0.000%

    No Known Activations