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

    Neuronpedia

    INDEX
    Explanations

    verifying conditions and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙨
    3.10
    𝙩
    2.95
    ியே
    2.72
    𝙙
    2.63
    ipos
    2.62
    𝙚
    2.59
    𝙜
    2.58
    𝙡
    2.58
    坻
    2.50
    𝙢
    2.49
    POSITIVE LOGITS
    nement
    2.27
    loj
    2.19
     batang
    2.18
     prib
    2.16
    친
    2.15
     cis
    2.02
     गुम
    2.02
     kep
    2.00
    പ്പ്
    1.97
     হস্ত
    1.96
    Act Density 0.696%

    No Known Activations