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

    Neuronpedia

    INDEX
    Explanations

    request processing and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    colm
    0.41
    kbd
    0.38
    pym
    0.36
    PasswordField
    0.36
     Mond
    0.35
    ドラ
    0.35
    বৈশাখ
    0.35
    svn
    0.34
    times
    0.34
    settes
    0.34
    POSITIVE LOGITS
     Assign
    0.45
     Rendering
    0.44
     variables
    0.43
     Action
    0.43
     Response
    0.43
     Params
    0.43
     action
    0.43
     Output
    0.43
     Scripts
    0.42
     assigning
    0.42
    Act Density 0.001%

    No Known Activations