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

    Neuronpedia

    INDEX
    Explanations

    places following the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    进入
    0.40
     nõ
    0.40
     прожи
    0.38
    arel
    0.37
     consect
    0.36
    ponge
    0.35
     افواج
    0.35
     nil
    0.35
    ellant
    0.35
    ža
    0.34
    POSITIVE LOGITS
     gym
    0.93
     zoo
    0.86
     beach
    0.84
     bakery
    0.81
     supermarket
    0.77
     courthouse
    0.77
     cafeteria
    0.75
     mailbox
    0.72
     woods
    0.72
     playground
    0.71
    Act Density 0.046%

    No Known Activations