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

    Neuronpedia

    INDEX
    Explanations

    performance comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗶
    0.56
    𝒊
    0.56
    ITZ
    0.53
    𝙸
    0.51
     lạnh
    0.51
     množství
    0.51
    ớp
    0.50
    ख्त
    0.50
    кових
    0.50
    òria
    0.50
    POSITIVE LOGITS
    m
    0.54
    otions
    0.51
    s
    0.51
    *
    0.51
    hdc
    0.50
    vue
    0.49
    w
    0.49
    ver
    0.49
    node
    0.48
    esse
    0.47
    Act Density 0.000%

    No Known Activations