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

    Neuronpedia

    INDEX
    Explanations

    get, receive, read, new, graph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    id
    0.32
    akes
    0.31
    isar
    0.29
    atan
    0.29
    ong
    0.28
    amas
    0.28
    ak
    0.27
    isan
    0.27
    ip
    0.27
    ivity
    0.27
    POSITIVE LOGITS
     महसूस
    0.34
     cherche
    0.33
     bier
    0.33
    ദ്ധി
    0.33
     může
    0.32
     wewnętr
    0.32
    ค์
    0.32
     Consejo
    0.32
     matériaux
    0.32
     preparar
    0.32
    Act Density 0.029%

    No Known Activations