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

    Neuronpedia

    INDEX
    Explanations

    fine-tuning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.39
    2
    1.33
    9
    1.31
    3
    1.30
    1
    1.23
    7
    1.22
    8
    1.14
    že
    1.13
    ist
    1.12
    4
    1.10
    POSITIVE LOGITS
     aHUS
    1.13
    ieth
    1.07
    埓
    0.99
     apartness
    0.98
    ୍
    0.98
    enarios
    0.97
     antics
    0.95
    𝐞
    0.95
    ógł
    0.94
     ก่อน
    0.94
    Act Density 0.061%

    No Known Activations