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

    Neuronpedia

    INDEX
    Explanations

    usa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fusion
    -0.08
    .entry
    -0.07
     fö
    -0.07
    ления
    -0.07
    creation
    -0.07
    ek
    -0.07
    知识
    -0.06
    sville
    -0.06
    리에
    -0.06
     channels
    -0.06
    POSITIVE LOGITS
    LOGIN
    0.07
    감
    0.07
    Database
    0.07
     ['-
    0.06
     signaling
    0.06
     свя
    0.06
    DMETHOD
    0.06
    Remark
    0.06
    =this
    0.06
    })"↵
    0.06
    Act Density 0.009%

    No Known Activations