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

    Neuronpedia

    INDEX
    Explanations

    conflict/war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    272
    -0.08
     brun
    -0.07
    (reader
    -0.07
     음식
    -0.07
    观点
    -0.07
    (struct
    -0.07
    意见
    -0.07
    (history
    -0.07
     plainly
    -0.07
     проз
    -0.07
    POSITIVE LOGITS
     distractions
    0.14
    忙
    0.13
     priorities
    0.12
     concurrently
    0.12
     tegelijkertijd
    0.12
     prioridades
    0.11
     distracted
    0.11
     distract
    0.11
     distracting
    0.11
    与此同时
    0.11
    Act Density 0.154%

    No Known Activations