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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chaining
    -0.07
     Encoding
    -0.06
     decay
    -0.06
    ematics
    -0.06
    oo
    -0.06
    (note
    -0.06
     genu
    -0.06
     incel
    -0.06
    ning
    -0.06
     carga
    -0.06
    POSITIVE LOGITS
     επισ
    0.07
     دری
    0.07
     specialised
    0.07
    ประม
    0.07
     услов
    0.06
    .StatusBadRequest
    0.06
     сна
    0.06
     evacuate
    0.06
     ब
    0.06
    .bam
    0.06
    Act Density 0.038%

    No Known Activations