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

    Neuronpedia

    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脚
    -0.06
    (match
    -0.06
     pie
    -0.06
    .dictionary
    -0.06
     legends
    -0.06
    .span
    -0.06
     balloon
    -0.05
     seemed
    -0.05
     print
    -0.05
     analogous
    -0.05
    POSITIVE LOGITS
    ?[
    0.07
     UIG
    0.07
     observational
    0.07
    >F
    0.07
    Yep
    0.07
    .zz
    0.07
     erotico
    0.06
    Ut
    0.06
     Brad
    0.06
    Ї
    0.06
    Act Density 0.000%

    No Known Activations