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

    Neuronpedia

    INDEX
    Explanations

    planets and exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     halves
    0.44
     aves
    0.42
     صاف
    0.41
    C
    0.41
     loaded
    0.40
    (!)
    0.40
     flops
    0.39
    iej
    0.38
     is
    0.38
     hypoxia
    0.36
    POSITIVE LOGITS
     設定
    0.53
    在美国
    0.50
     美国
    0.50
     postav
    0.50
    EditText
    0.48
     リビング
    0.48
     システム
    0.48
     tissus
    0.46
     svjets
    0.46
    LEXPORT
    0.46
    Act Density 0.001%

    No Known Activations