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

    Neuronpedia

    INDEX
    Explanations

    Helix, ich, alis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কিড
    0.45
     Rock
    0.41
    Broadcast
    0.40
     रोमन
    0.39
    徃
    0.39
    yet
    0.38
     Yet
    0.38
     Cha
    0.38
    حيان
    0.38
     borderColor
    0.37
    POSITIVE LOGITS
     pickled
    0.40
     pron
    0.39
     pickle
    0.37
     পী
    0.37
     పి
    0.36
    蚤
    0.36
     crushed
    0.36
     pronunci
    0.35
     pickles
    0.35
    굴
    0.35
    Act Density 0.000%

    No Known Activations