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

    Neuronpedia

    INDEX
    Explanations

    client application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    modb
    -0.88
    𝕒
    -0.86
    wapV
    -0.83
    olov
    -0.77
     accuracy
    -0.76
    vč
    -0.75
    lias
    -0.74
    Mockito
    -0.74
     машины
    -0.73
    spira
    -0.73
    POSITIVE LOGITS
     client
    2.61
    客户端
    2.16
     clients
    2.11
    client
    1.93
    CLIENT
    1.77
    Clients
    1.73
     Client
    1.71
     Clients
    1.64
    Client
    1.61
     CLIENT
    1.61
    Act Density 0.112%

    No Known Activations