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

    Neuronpedia

    INDEX
    Explanations

    database configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     円
    -0.08
     бор
    -0.08
    ณะ
    -0.08
    .mime
    -0.08
    Faction
    -0.08
    .lon
    -0.08
     bitterness
    -0.08
    .chapter
    -0.08
    agize
    -0.08
     Furious
    -0.08
    POSITIVE LOGITS
     replicas
    0.09
    rollback
    0.08
    モデル
    0.08
     modelos
    0.07
     rollout
    0.07
    Automatically
    0.07
    ロ
    0.07
    iscal
    0.07
    aston
    0.07
     detects
    0.07
    Act Density 0.002%

    No Known Activations