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

    Neuronpedia

    INDEX
    Explanations

    expand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spectrum
    -0.07
    pet
    -0.07
     deposits
    -0.07
    .course
    -0.06
     service
    -0.06
    収
    -0.06
     provides
    -0.06
    tti
    -0.06
    uentes
    -0.06
     Architecture
    -0.06
    POSITIVE LOGITS
    .expand
    0.07
    -expand
    0.07
    Expand
    0.07
    三级
    0.07
    Clickable
    0.07
     Breitbart
    0.07
    .SelectedItems
    0.07
    ndon
    0.06
     Wrestling
    0.06
     Expanded
    0.06
    Act Density 0.005%

    No Known Activations