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

    Neuronpedia

    INDEX
    Explanations

    names (common prefixes)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.37
    是
    0.35
     be
    0.34
    外
    0.33
    ↵
    0.31
     The
    0.31
    我
    0.30
     velha
    0.29
    م
    0.29
    ↵↵
    0.29
    POSITIVE LOGITS
     मेथड
    0.32
    uous
    0.29
    astrophe
    0.28
    <unused1061>
    0.28
    ority
    0.27
    centaje
    0.27
    Default
    0.27
    Qaeda
    0.26
    жность
    0.26
    $,
    0.25
    Act Density 0.010%

    No Known Activations