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

    Neuronpedia

    INDEX
    Explanations

    future, servers, or terror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    纮
    0.45
     আবরণ
    0.44
    ელ
    0.43
    龵
    0.40
    Kenn
    0.39
    熊本
    0.39
    슈
    0.39
     Reichs
    0.38
    砧
    0.38
    횽
    0.38
    POSITIVE LOGITS
     fairly
    0.45
     sandbox
    0.43
     zar
    0.40
     mee
    0.40
    uster
    0.39
     causa
    0.38
    也就是说
    0.38
     they
    0.38
     requirements
    0.37
     causal
    0.37
    Act Density 0.000%

    No Known Activations