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

    Neuronpedia

    INDEX
    Explanations

    code and math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replen
    -0.10
     anglers
    -0.09
     superintendent
    -0.09
    Prin
    -0.09
     supplementation
    -0.09
     interviewing
    -0.08
     mqtt
    -0.08
    Podcast
    -0.08
     capita
    -0.08
    …and
    -0.08
    POSITIVE LOGITS
    _expr
    0.15
     Mathemat
    0.13
     Algebra
    0.12
     symbolic
    0.11
     algebra
    0.11
    Expr
    0.11
     Expr
    0.11
    .Expr
    0.10
    .expr
    0.10
     simpl
    0.10
    Act Density 0.017%

    No Known Activations