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

    Neuronpedia

    INDEX
    Explanations

    AI and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ప్రక
    0.44
    వేయ
    0.44
     devotee
    0.43
    StudentNo
    0.42
     Lesser
    0.42
     방식으로
    0.42
     purest
    0.42
     melee
    0.42
     Digests
    0.42
     boulder
    0.42
    POSITIVE LOGITS
    \]
    0.52
    ll
    0.51
    ্যান্ট
    0.49
    اری
    0.49
    cour
    0.45
    াস
    0.45
    hit
    0.43
    卫生
    0.43
    纵
    0.43
    眅
    0.42
    Act Density 0.003%

    No Known Activations