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

    Neuronpedia

    INDEX
    Explanations

    freq

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empleado
    -0.07
     render
    -0.07
    cheon
    -0.07
    �
    -0.06
    .dense
    -0.06
    .centerX
    -0.06
     custody
    -0.06
    也没什么
    -0.06
    -no
    -0.06
     elderly
    -0.06
    POSITIVE LOGITS
    ascar
    0.07
     MIC
    0.07
    אס
    0.07
    แสด
    0.07
     AQ
    0.07
     aprend
    0.07
    UTIL
    0.07
    斝
    0.06
    gresql
    0.06
    監
    0.06
    Act Density 0.003%

    No Known Activations