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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tulsa
    -0.07
     Feed
    -0.06
    .There
    -0.06
     cycling
    -0.06
     Action
    -0.06
    Radians
    -0.06
    Ray
    -0.06
    rawn
    -0.06
     nextPage
    -0.06
     })
    -0.06
    POSITIVE LOGITS
     drainage
    0.07
    lâm
    0.06
     коміс
    0.06
    लब
    0.06
     побач
    0.06
    <TEntity
    0.06
     residues
    0.06
     **/
↵
    0.06
    των
    0.06
     {:?}",
    0.06
    Act Density 0.001%

    No Known Activations