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

    Neuronpedia

    INDEX
    Explanations

    x-ray for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Calab
    0.40
     wide
    0.38
    れ
    0.38
     few
    0.37
    enter
    0.37
     dismay
    0.37
    Co
    0.37
    lbs
    0.37
    itans
    0.36
     abound
    0.36
    POSITIVE LOGITS
    ωσ
    0.42
    ivar
    0.42
     κατο
    0.41
    茱
    0.37
     সম্ভব
    0.36
     viewHolder
    0.35
     !_
    0.35
    场景
    0.35
    っちゃ
    0.35
    ợ
    0.35
    Act Density 0.000%

    No Known Activations