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

    Neuronpedia

    INDEX
    Explanations

    AWS HA Pair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.50
    VerFile
    0.47
    楼主
    0.47
     Idani
    0.46
    蔑
    0.46
    ема
    0.46
    一篇
    0.46
    岧
    0.46
    嵬
    0.45
    bollah
    0.45
    POSITIVE LOGITS
     known
    0.51
    J
    0.48
     für
    0.47
    CD
    0.47
     bridge
    0.46
     famously
    0.45
    WC
    0.45
     tooling
    0.45
    Buk
    0.45
     Während
    0.44
    Act Density 0.000%

    No Known Activations