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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    陬
    -0.07
    :i
    -0.07
    嘴角
    -0.07
     조금
    -0.07
    JNIEnv
    -0.07
    冏
    -0.07
    葳
    -0.07
     kvinn
    -0.07
     veh
    -0.07
     li
    -0.07
    POSITIVE LOGITS
     illumination
    0.07
    켈
    0.07
    .Type
    0.07
    𫘪
    0.07
    awks
    0.07
    킨
    0.07
    疾
    0.07
    �
    0.06
     herald
    0.06
     Adams
    0.06
    Act Density 0.015%

    No Known Activations