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

    Neuronpedia

    INDEX
    Explanations

    Sri

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     L
    0.67
    L
    0.57
    Lance
    0.48
    CHREIB
    0.44
     Л
    0.44
     الل
    0.43
    Ｌ
    0.43
     Lance
    0.43
     Lankan
    0.42
    Л
    0.42
    POSITIVE LOGITS
    iko
    0.46
    ikit
    0.44
    ikon
    0.41
    pire
    0.40
    ophilia
    0.40
    imbo
    0.38
     גדול
    0.38
    ink
    0.37
    coh
    0.36
    yaw
    0.36
    Act Density 0.000%

    No Known Activations