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

    Neuronpedia

    INDEX
    Explanations

    signal or champion evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.56
    在這個
    0.53
    Fork
    0.52
    ഹ്
    0.52
     दट
    0.50
     Graz
    0.49
    尕
    0.48
    Graz
    0.47
    loadNpm
    0.47
    ೯
    0.47
    POSITIVE LOGITS
    ش
    0.53
    </th>
    0.51
    antro
    0.43
    ث
    0.43
    idders
    0.42
     kosong
    0.41
     mendorong
    0.41
    </h3>
    0.40
     TLR
    0.40
    ikl
    0.39
    Act Density 0.000%

    No Known Activations