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

    Neuronpedia

    INDEX
    Explanations

    code block structure diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zur
    0.40
     poth
    0.38
    cripts
    0.37
     técn
    0.37
    ________
    0.37
     _____________
    0.36
    ofi
    0.36
    넋
    0.35
     technically
    0.34
    CONTEXT
    0.34
    POSITIVE LOGITS
     >
    0.59
    |>
    0.48
    ＞
    0.47
    >
    0.47
     |
    0.46
     $>$
    0.45
    >(
    0.44
     >>
    0.44
    0.43
    ']>
    0.42
    Act Density 0.005%

    No Known Activations