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

    Neuronpedia

    INDEX
    Explanations

    uncertainty and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hatte
    0.28
    Mutable
    0.24
    vede
    0.24
    uk
    0.22
    Message
    0.22
    zieht
    0.22
    曌
    0.21
    at
    0.21
     mé
    0.21
    ův
    0.21
    POSITIVE LOGITS
    전
    0.27
    음
    0.25
    به
    0.25
    기
    0.25
    대
    0.25
    g
    0.24
    개
    0.24
    子供
    0.24
     организма
    0.24
    초
    0.23
    Act Density 0.148%

    No Known Activations