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

    Neuronpedia

    INDEX
    Explanations

    * followed by ** or PP_00

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瑞士
    0.39
     Electron
    0.38
     Residents
    0.38
     Maple
    0.38
    ῴ
    0.37
     residents
    0.37
     Outcome
    0.37
    葆
    0.37
    genheim
    0.37
     shelled
    0.37
    POSITIVE LOGITS
     agora
    0.45
    vigor
    0.41
    잡
    0.40
     Dí
    0.40
    Now
    0.39
     карти
    0.38
    Bowling
    0.37
    By
    0.37
     이제
    0.37
    canic
    0.36
    Act Density 0.000%

    No Known Activations