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

    Neuronpedia

    INDEX
    Explanations

    code operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sync
    -0.07
    Mas
    -0.07
    -policy
    -0.07
     Bedford
    -0.07
    ças
    -0.07
    μία
    -0.07
    .’↵↵
    -0.07
     pros
    -0.06
    _visited
    -0.06
    SHOT
    -0.06
    POSITIVE LOGITS
    appers
    0.07
    ++){
    0.07
     působ
    0.07
     scop
    0.07
    .Per
    0.07
     prot
    0.06
     จะ
    0.06
    ajes
    0.06
    aje
    0.06
    olid
    0.06
    Act Density 0.008%

    No Known Activations