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

    Neuronpedia

    INDEX
    Explanations

    . Paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ulf
    -0.73
    yesha
    -0.71
    構造
    -0.69
    ắt
    -0.68
     пост
    -0.67
     kiel
    -0.65
     clusters
    -0.65
     ossia
    -0.65
    行動
    -0.65
    structural
    -0.64
    POSITIVE LOGITS
    ndes
    0.72
     List
    0.68
     heard
    0.68
     estudiar
    0.67
     looser
    0.66
     casket
    0.66
    库存
    0.65
    smi
    0.63
     Küche
    0.63
     viewport
    0.63
    Act Density 0.083%

    No Known Activations