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

    Neuronpedia

    INDEX
    Explanations

    save as type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tâ
    0.43
     ESTIM
    0.40
    튿
    0.39
    രീ
    0.38
    斕
    0.38
     Equality
    0.38
    ullahi
    0.38
    面上
    0.37
     координа
    0.37
     महासभा
    0.37
    POSITIVE LOGITS
     outflow
    0.42
     formalities
    0.41
    Comic
    0.41
    depth
    0.39
    Par
    0.39
    deserialize
    0.39
    ලය
    0.38
    beth
    0.38
    German
    0.38
    comic
    0.38
    Act Density 0.000%

    No Known Activations