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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    平原
    -0.07
    WebView
    -0.07
    งาม
    -0.07
    .CODE
    -0.07
     primer
    -0.07
     המון
    -0.07
    征集
    -0.07
    滩
    -0.07
     gravel
    -0.06
    펜
    -0.06
    POSITIVE LOGITS
    驷
    0.09
     şirket
    0.07
     //(
    0.07
     bitwise
    0.07
    ancellationToken
    0.07
    ⚱
    0.06
    蠖
    0.06
    ∘
    0.06
    겁
    0.06
    ↵	↵
    0.06
    Act Density 0.013%

    No Known Activations