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

    Neuronpedia

    INDEX
    Explanations

    Ascites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ●●●●●●●●●●●●●●●●
    -0.07
    biên
    -0.07
    罗
    -0.07
     Tor
    -0.06
     Bon
    -0.06
     desper
    -0.06
    �
    -0.06
    .linkLabel
    -0.06
    celona
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     Oil
    0.07
     yogurt
    0.07
     stray
    0.06
    泉
    0.06
     wishing
    0.06
     Crafting
    0.06
    Pose
    0.06
     Firearms
    0.06
     lowers
    0.06
    如下
    0.06
    Act Density 0.005%

    No Known Activations