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

    Neuronpedia

    INDEX
    Explanations

    intelligent assistants capable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അവ
    0.51
    zenes
    0.44
    ems
    0.39
    hern
    0.39
    rient
    0.38
    astr
    0.38
    zens
    0.38
    ms
    0.37
    opatra
    0.37
    вости
    0.37
    POSITIVE LOGITS
    шена
    0.46
     Inde
    0.41
     Personnel
    0.40
    ર્ડ
    0.39
     Regan
    0.39
    Personnel
    0.38
    indeki
    0.38
     graciously
    0.38
     Bina
    0.38
     Kindly
    0.38
    Act Density 0.001%

    No Known Activations