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

    Neuronpedia

    INDEX
    Explanations

    stories or backstories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     znale
    0.81
     poč
    0.81
    bala
    0.76
    한국
    0.74
    ujian
    0.74
     Bahnhof
    0.73
    ޚ
    0.72
    ativen
    0.72
    כים
    0.72
     こと
    0.72
    POSITIVE LOGITS
    wards
    1.26
    grond
    1.26
    hoe
    1.23
    hoes
    1.21
    propagation
    1.19
    sliding
    1.17
    gam
    1.12
    drops
    1.12
    ronym
    1.10
    door
    1.08
    Act Density 0.081%

    No Known Activations