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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appe
    -0.07
    undles
    -0.06
     swung
    -0.06
     Pretty
    -0.06
    Two
    -0.06
    iß
    -0.06
     magically
    -0.06
    Schema
    -0.06
     meshes
    -0.06
     Companies
    -0.06
    POSITIVE LOGITS
     Анг
    0.07
     Chapel
    0.06
     стара
    0.06
     Bart
    0.06
    -Ф
    0.06
    RAND
    0.06
     PED
    0.06
    الم
    0.06
     HG
    0.06
    .VERTICAL
    0.06
    Act Density 0.081%

    No Known Activations