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

    Neuronpedia

    INDEX
    Explanations

    Option 1, 2, 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ką
    0.49
    その後
    0.48
    愔
    0.47
    CA
    0.46
    ான
    0.44
    ost
    0.44
    时间
    0.43
    みます
    0.43
    ');
    0.43
    URN
    0.42
    POSITIVE LOGITS
     relish
    0.61
     brine
    0.52
     splurge
    0.52
     outsource
    0.51
     serve
    0.48
     mulch
    0.47
    risome
    0.47
     vaccines
    0.47
     rhino
    0.47
     rupee
    0.47
    Act Density 0.108%

    No Known Activations