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

    Neuronpedia

    INDEX
    Explanations

    compound noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.43
     startet
    0.42
    。",
    0.41
     elems
    0.39
     airports
    0.39
     colnames
    0.37
     zippers
    0.37
     pradesh
    0.36
     ginseng
    0.36
     bicicleta
    0.36
    POSITIVE LOGITS
    o
    0.46
     Emeritus
    0.40
    те
    0.38
    <b>
    0.38
    ﻛ
    0.35
    <a>
    0.35
     muchas
    0.35
     Kapol
    0.35
    🈂
    0.35
    etzes
    0.34
    Act Density 0.214%

    No Known Activations