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

    Neuronpedia

    INDEX
    Explanations

    parties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mul
    -0.07
     شاخه
    -0.07
    (scope
    -0.06
    今年
    -0.06
    เอง
    -0.06
     founder
    -0.06
    創
    -0.06
     свят
    -0.06
    orf
    -0.06
     chiff
    -0.06
    POSITIVE LOGITS
     party
    0.12
     parties
    0.09
    -party
    0.08
     partes
    0.08
     Party
    0.07
    Sync
    0.07
     Rights
    0.07
    Park
    0.07
     Labour
    0.07
     Tat
    0.07
    Act Density 0.011%

    No Known Activations