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

    Neuronpedia

    INDEX
    Explanations

    key-value structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AOrdenar
    0.31
    ukiyoe
    0.29
    <unused206>
    0.28
    \%).
    0.27
    玾
    0.27
    ClrBit
    0.27
    னமாக
    0.26
    🙈
    0.26
     взгля
    0.26
    溸
    0.26
    POSITIVE LOGITS
    :
    0.64
    ：
    0.57
     :
    0.47
     =
    0.41
    ::
    0.40
    ="
    0.38
    =
    0.38
        
    0.38
    :,
    0.38
    0.38
    Act Density 0.707%

    No Known Activations