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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tasmania
    -0.07
    ��
    -0.06
     undefeated
    -0.06
    लग
    -0.06
    距
    -0.06
    ्भ
    -0.06
     baked
    -0.06
    Streaming
    -0.06
     Kra
    -0.06
    otle
    -0.06
    POSITIVE LOGITS
     влади
    0.07
     적
    0.06
    /en
    0.06
    WF
    0.06
    .school
    0.06
    WP
    0.06
     ㅇㅇ
    0.06
    妻
    0.06
     MSI
    0.06
    .cmd
    0.06
    Act Density 0.002%

    No Known Activations