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

    Neuronpedia

    INDEX
    Explanations

    server security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     января
    -0.07
    xious
    -0.07
    などが
    -0.07
     singer
    -0.07
     white
    -0.07
     pressure
    -0.06
    等多种
    -0.06
     że
    -0.06
    总觉得
    -0.06
    的各种
    -0.06
    POSITIVE LOGITS
    تطبيق
    0.08
     Friendship
    0.08
    עיל
    0.07
     Arrival
    0.07
     carrots
    0.07
    דוד
    0.07
    omba
    0.07
    Robin
    0.07
     Governance
    0.07
    容纳
    0.07
    Act Density 0.046%

    No Known Activations