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

    Neuronpedia

    INDEX
    Explanations

    visibility and seeing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वणी
    0.39
    0.39
    Allister
    0.38
    ⎆
    0.37
    askell
    0.37
    語
    0.37
    נס
    0.37
    werten
    0.36
    жкой
    0.36
     လုပ်
    0.36
    POSITIVE LOGITS
     visibility
    1.98
     Visibility
    1.71
     visible
    1.68
    Visibility
    1.63
     zicht
    1.51
    visibility
    1.50
    visible
    1.49
     visibles
    1.46
     Visible
    1.42
    Visible
    1.39
    Act Density 0.065%

    No Known Activations