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

    Neuronpedia

    INDEX
    Explanations

    encoded data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一波
    -0.08
    곸
    -0.07
    Criteria
    -0.07
     fitte
    -0.07
     nerves
    -0.07
    thenReturn
    -0.07
    ottle
    -0.07
    _MESH
    -0.06
    神通
    -0.06
     pods
    -0.06
    POSITIVE LOGITS
     SwiftUI
    0.07
    _CUDA
    0.07
    rij
    0.07
    扎
    0.07
    מסעדה
    0.06
     Over
    0.06
    ----------------------------
    0.06
     Pale
    0.06
     skip
    0.06
     Hou
    0.06
    Act Density 0.005%

    No Known Activations