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

    Neuronpedia

    INDEX
    Explanations

    plot ticks and labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     месте
    -0.07
    evaluation
    -0.07
    jian
    -0.07
    жу
    -0.06
    ся
    -0.06
    ooke
    -0.06
    描
    -0.06
    .just
    -0.06
    層
    -0.06
    ("../
    -0.06
    POSITIVE LOGITS
    _ut
    0.06
    (sm
    0.06
    _Settings
    0.06
     helfen
    0.06
     GENERATED
    0.06
    인증
    0.06
    しており
    0.06
    ΜΠ
    0.06
    Statics
    0.06
    NotAllowed
    0.06
    Act Density 0.011%

    No Known Activations