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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    土
    -0.08
     padre
    -0.07
     Petite
    -0.07
    Longrightarrow
    -0.07
     Educação
    -0.07
    姓
    -0.07
    .service
    -0.07
    巴黎
    -0.07
     interest
    -0.07
    .NoArgsConstructor
    -0.07
    POSITIVE LOGITS
    ISODE
    0.07
    oref
    0.07
    足够的
    0.07
    .buffer
    0.07
     중요한
    0.07
    日后
    0.06
     prevalence
    0.06
    提供的
    0.06
    .ColumnName
    0.06
    инф
    0.06
    Act Density 0.000%

    No Known Activations