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

    Neuronpedia

    INDEX
    Explanations

    personal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jeff
    -0.07
     Stephens
    -0.07
    ypes
    -0.07
    -slot
    -0.07
    ELS
    -0.07
     ALS
    -0.07
    UserCode
    -0.06
    ്
    -0.06
    óng
    -0.06
     bè
    -0.06
    POSITIVE LOGITS
    画像
    0.08
    传授
    0.08
    陂
    0.07
    学习贯彻
    0.07
    න
    0.07
    姱
    0.07
     dimin
    0.07
    _permission
    0.07
     worked
    0.07
    Nome
    0.07
    Act Density 0.007%

    No Known Activations