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

    Neuronpedia

    INDEX
    Explanations

    vable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spotting
    -0.07
     eh
    -0.07
     Tell
    -0.07
     pockets
    -0.07
    Explore
    -0.07
    情形
    -0.07
    龛
    -0.07
    Gallery
    -0.06
    𝐃
    -0.06
     genetic
    -0.06
    POSITIVE LOGITS
    煋
    0.07
    קיימת
    0.07
    �
    0.07
    .ModelSerializer
    0.07
    �
    0.07
    موظ
    0.07
    私
    0.07
    _af
    0.07
    芫
    0.06
    技法
    0.06
    Act Density 0.001%

    No Known Activations