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

    Neuronpedia

    INDEX
    Explanations

    -S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COURT
    -0.08
    着急
    -0.07
    呼叫
    -0.07
    burgh
    -0.07
    赶上
    -0.07
     interstate
    -0.07
    /_
    -0.07
    /ph
    -0.07
    하며
    -0.06
    זכ
    -0.06
    POSITIVE LOGITS
     bezpoś
    0.07
    ¯¯
    0.07
     oppos
    0.07
    stroy
    0.06
    ozy
    0.06
     profits
    0.06
    وحد
    0.06
     październ
    0.06
    报复
    0.06
    ماذا
    0.06
    Act Density 0.001%

    No Known Activations