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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vaping
    -0.09
     Instagram
    -0.09
     fandom
    -0.09
    Instagram
    -0.09
     creëren
    -0.09
     emojis
    -0.09
     mqtt
    -0.09
     emoji
    -0.08
     hashtag
    -0.08
     instagram
    -0.08
    POSITIVE LOGITS
    _solver
    0.15
     solver
    0.15
    Solver
    0.15
     Solver
    0.14
    solver
    0.13
     solve
    0.13
     algorithms
    0.12
     Solve
    0.12
    solve
    0.12
    .solve
    0.12
    Act Density 0.010%

    No Known Activations