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

    Neuronpedia

    INDEX
    Explanations

    map and chart visualization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ắ
    0.41
     みたい
    0.40
    पटना
    0.40
    Mock
    0.39
     проблема
    0.39
     marka
    0.39
    ক্তির
    0.39
    checksum
    0.39
    Completion
    0.39
    ালার
    0.38
    POSITIVE LOGITS
     separated
    0.38
     corre
    0.38
     serr
    0.37
     lel
    0.36
     is
    0.35
     biss
    0.35
     elemental
    0.35
     differentiated
    0.34
     pulp
    0.34
     are
    0.34
    Act Density 0.002%

    No Known Activations