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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     huis
    -0.07
     At
    -0.07
    —as
    -0.06
     As
    -0.06
    krát
    -0.06
     Essentially
    -0.06
     Ül
    -0.06
    idae
    -0.06
     instances
    -0.06
    (album
    -0.05
    POSITIVE LOGITS
    react
    0.07
     无
    0.07
     الوص
    0.06
     时
    0.06
    .blob
    0.06
    ิต
    0.06
    calculator
    0.06
    GD
    0.06
     vowed
    0.06
    ीर
    0.06
    Act Density 0.082%

    No Known Activations