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

    Neuronpedia

    INDEX
    Explanations

    back and forth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     runners
    -0.08
     przew
    -0.07
     scarcity
    -0.07
     probability
    -0.07
     euth
    -0.07
     مي
    -0.07
     importance
    -0.07
     중요
    -0.07
    цій
    -0.07
     نصب
    -0.07
    POSITIVE LOGITS
    双方
    0.17
     échanges
    0.16
     exchanges
    0.16
     exchanged
    0.15
     Exchanges
    0.15
     intercambio
    0.15
    互动
    0.14
     exchanging
    0.14
    بادل
    0.14
    交流
    0.13
    Act Density 0.079%

    No Known Activations