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

    Neuronpedia

    INDEX
    Explanations

    requesting image or document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    很简单
    0.39
     fat
    0.38
     çar
    0.38
     tranquille
    0.37
    比較的
    0.37
     relaxed
    0.37
     tranquilo
    0.37
     Navigator
    0.36
    haupt
    0.36
    碎
    0.36
    POSITIVE LOGITS
     unfortunately
    0.60
    Unfortunately
    0.57
     Unfortunately
    0.55
     malheureusement
    0.54
     visual
    0.53
     uploaded
    0.51
     uploads
    0.51
     Unable
    0.51
     physically
    0.50
     described
    0.48
    Act Density 0.012%

    No Known Activations