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

    Neuronpedia

    INDEX
    Explanations

    local spots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     symbolName
    0.44
    ahiran
    0.43
    ㄥ
    0.43
    ipada
    0.42
     군
    0.41
     जुड़ा
    0.41
     పని
    0.41
     전시
    0.41
     Initiatives
    0.40
    oward
    0.40
    POSITIVE LOGITS
    Ont
    0.51
    𝐅
    0.46
    ين
    0.45
    𝐑
    0.44
    Budget
    0.43
    𝐈
    0.43
    Strict
    0.43
    𝐧
    0.43
     folgender
    0.42
     تاريخ
    0.41
    Act Density 0.000%

    No Known Activations