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

    Neuronpedia

    INDEX
    Explanations

    cluster

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Session
    -0.08
     possibilities
    -0.08
     foll
    -0.08
     expiration
    -0.08
    一
    -0.07
     jade
    -0.07
    �
    -0.07
    bole
    -0.07
    oss
    -0.07
    _AB
    -0.07
    POSITIVE LOGITS
     clusters
    0.08
    翥
    0.07
    _Device
    0.06
     cluster
    0.06
    _cluster
    0.06
    紧凑
    0.06
    ParticleSystem
    0.06
    Cluster
    0.06
    清华大学
    0.06
    .Cluster
    0.06
    Act Density 0.008%

    No Known Activations