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

    Neuronpedia

    INDEX
    Explanations

    playground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AA
    -0.07
    )];
    -0.07
     Thick
    -0.06
     backs
    -0.06
     миллион
    -0.06
    andro
    -0.06
    庆
    -0.06
     Break
    -0.06
     Hawk
    -0.06
    总队
    -0.06
    POSITIVE LOGITS
     QMessageBox
    0.07
     DOC
    0.07
    Charset
    0.07
     Ministério
    0.07
     dietary
    0.07
     destinations
    0.07
     Emer
    0.07
     órg
    0.06
     País
    0.06
    沿海
    0.06
    Act Density 0.013%

    No Known Activations