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

    Neuronpedia

    INDEX
    Explanations

    http parameters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    0.94
     ......
    0.87
     -(
    0.86
     **
    0.86
     .......
    0.83
     ....
    0.82
     ++
    0.82
     ........
    0.82
     -.
    0.81
     –
    0.81
    POSITIVE LOGITS
    <unused0>
    0.74
    முற
    0.64
    instead
    0.64
    Instead
    0.60
    +
    0.60
    Fach
    0.59
    does
    0.58
    ဟု
    0.58
    Charm
    0.58
    <unused1056>
    0.58
    Act Density 0.000%

    No Known Activations