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

    Neuronpedia

    INDEX
    Explanations

    om beach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     there
    0.78
     saddened
    0.74
     unhappy
    0.73
     enticing
    0.68
    وتی
    0.66
     encouraging
    0.65
     accessible
    0.65
    异
    0.65
     disheart
    0.64
    ㅓ
    0.64
    POSITIVE LOGITS
    wir
    0.94
     diri
    0.85
    pped
    0.76
    ulsory
    0.75
     meningkat
    0.75
     dirinya
    0.72
     skyrock
    0.71
     già
    0.71
     sustancias
    0.71
    ؘ
    0.71
    Act Density 0.000%

    No Known Activations